Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.8335. Min Act: -0.1700
Data Index: 2462095 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.7085. Min Act: -0.1700
Data Index: 1712587 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.7085. Min Act: -0.1700
Data Index: 2553917 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.7085. Min Act: -0.1700
Data Index: 3541361 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.6460. Min Act: -0.1700
Data Index: 3229935 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.6460. Min Act: -0.1700
Data Index: 1442744 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.5835. Min Act: -0.1700
Data Index: 3302523 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.5835. Min Act: -0.1700
Data Index: 7676149 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.5835. Min Act: -0.1700
Data Index: 4277424 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.5210. Min Act: -0.1700
Data Index: 7806940 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.4585. Min Act: -0.1700
Data Index: 6762366 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.4273. Min Act: -0.1700
Data Index: 4118289 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3960. Min Act: -0.1700
Data Index: 6913028 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3960. Min Act: -0.1700
Data Index: 7207329 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3960. Min Act: -0.1700
Data Index: 2741304 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3648. Min Act: -0.1700
Data Index: 3595996 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3648. Min Act: -0.1700
Data Index: 4921121 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3648. Min Act: -0.1700
Data Index: 8410940 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3648. Min Act: -0.1700
Data Index: 5681996 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8335. Min Range: -7.8335
Max Act: 7.3023. Min Act: -0.1700
Data Index: 875487 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19