Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1858. Min Range: -6.1858
Max Act: 6.1858. Min Act: -0.1700
Data Index: 6258493 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1858. Min Range: -6.1858
Max Act: 6.1233. Min Act: -0.1700
Data Index: 6258492 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1858. Min Range: -6.1858
Max Act: 6.0920. Min Act: -0.1700
Data Index: 6258494 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1858. Min Range: -6.1858
Max Act: 6.0920. Min Act: -0.1700
Data Index: 1931754 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1858. Min Range: -6.1858
Max Act: 6.0295. Min Act: -0.1700
Data Index: 8789036 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.9983. Min Act: -0.1700
Data Index: 6258502 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.9670. Min Act: -0.1700
Data Index: 1940857 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.9983. Min Act: -0.1700
Data Index: 6258503 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.9045. Min Act: -0.1700
Data Index: 5501557 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.8733. Min Act: -0.1700
Data Index: 5858022 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7795. Min Act: -0.1700
Data Index: 2713255 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.8420. Min Act: -0.1700
Data Index: 2051471 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.8108. Min Act: -0.1700
Data Index: 7898080 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5592654 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1837047 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.8108. Min Act: -0.1700
Data Index: 2235191 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7483. Min Act: -0.1700
Data Index: 4056262 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7483. Min Act: -0.1700
Data Index: 3442629 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.7795. Min Act: -0.1700
Data Index: 2629596 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1858. Min Range: -6.1858
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4111210 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19