Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1802. Min Range: -4.1802
Max Act: 4.1802. Min Act: -0.1700
Data Index: 5659880 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1802. Min Range: -4.1802
Max Act: 4.1490. Min Act: -0.1700
Data Index: 1376147 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1802. Min Range: -4.1802
Max Act: 4.0240. Min Act: -0.1700
Data Index: 1944591 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9927. Min Act: -0.1700
Data Index: 4476210 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9614. Min Act: -0.1700
Data Index: 5096162 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9927. Min Act: -0.1700
Data Index: 4846725 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9614. Min Act: -0.1700
Data Index: 7293949 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9614. Min Act: -0.1700
Data Index: 3584101 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9614. Min Act: -0.1700
Data Index: 7783065 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 6354737 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9302. Min Act: -0.1700
Data Index: 459249 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9302. Min Act: -0.1700
Data Index: 7092690 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9302. Min Act: -0.1700
Data Index: 3689181 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4414086 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 7329563 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 4424026 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 1354214 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 6286346 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 2216550 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1802. Min Range: -4.1802
Max Act: 3.8989. Min Act: -0.1700
Data Index: 2494313 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19