Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1173 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.9494. Min Act: -0.1700
Data Index: 1933316 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.8869. Min Act: -0.1699
Data Index: 1933321 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.8244. Min Act: -0.1700
Data Index: 1933313 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.8244. Min Act: -0.1700
Data Index: 1933309 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.7619. Min Act: -0.1700
Data Index: 1933315 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6994. Min Act: -0.1700
Data Index: 1933317 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6994. Min Act: -0.1700
Data Index: 1933324 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6994. Min Act: -0.1700
Data Index: 7870458 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6369. Min Act: -0.1700
Data Index: 1933310 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6994. Min Act: -0.1700
Data Index: 1933312 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.6369. Min Act: -0.1700
Data Index: 8270227 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.5744. Min Act: -0.1700
Data Index: 1933307 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.5744. Min Act: -0.1700
Data Index: 2922774 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.5744. Min Act: -0.1700
Data Index: 1933308 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.5119. Min Act: -0.1700
Data Index: 1912307 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.5744. Min Act: -0.1700
Data Index: 1933318 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.4494. Min Act: -0.1700
Data Index: 4672377 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.4494. Min Act: -0.1700
Data Index: 8270231 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.4494. Min Act: -0.1700
Data Index: 1933311 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9494. Min Range: -13.9494
Max Act: 13.4494. Min Act: -0.1700
Data Index: 4894541 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19