Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2597. Min Range: -10.2597
Max Act: 10.2597. Min Act: -0.1700
Data Index: 5523806 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2597. Min Range: -10.2597
Max Act: 10.1972. Min Act: -0.1700
Data Index: 232244 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 5251724 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 1729597 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.8847. Min Act: -0.1700
Data Index: 1871499 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.8222. Min Act: -0.1700
Data Index: 7095970 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.8847. Min Act: -0.1700
Data Index: 8717710 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.7597. Min Act: -0.1700
Data Index: 7023611 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 4123117 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 373898 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 1418165 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 3554232 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.5722. Min Act: -0.1700
Data Index: 6944341 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6347. Min Act: -0.1700
Data Index: 1807104 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6347. Min Act: -0.1700
Data Index: 6515411 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.6347. Min Act: -0.1700
Data Index: 1393436 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.5722. Min Act: -0.1700
Data Index: 3232276 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.5722. Min Act: -0.1700
Data Index: 3195991 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.5097. Min Act: -0.1700
Data Index: 7274576 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2597. Min Range: -10.2597
Max Act: 9.5722. Min Act: -0.1700
Data Index: 6315382 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19