Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.5745. Min Act: -0.1700
Data Index: 2304674 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4138812 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4495. Min Act: -0.1700
Data Index: 4111970 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4495. Min Act: -0.1700
Data Index: 6344402 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4182. Min Act: -0.1700
Data Index: 8204689 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4495. Min Act: -0.1700
Data Index: 2915090 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4495. Min Act: -0.1700
Data Index: 4019152 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4495. Min Act: -0.1700
Data Index: 6059401 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4182. Min Act: -0.1700
Data Index: 6533422 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4182. Min Act: -0.1700
Data Index: 2973749 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.4182. Min Act: -0.1700
Data Index: 4931316 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3870. Min Act: -0.1700
Data Index: 3948316 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3870. Min Act: -0.1700
Data Index: 8686885 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3870. Min Act: -0.1700
Data Index: 2715658 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3557. Min Act: -0.1700
Data Index: 1271846 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3557. Min Act: -0.1700
Data Index: 3899605 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3557. Min Act: -0.1700
Data Index: 5764283 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3245. Min Act: -0.1700
Data Index: 4844215 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4801085 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5745. Min Range: -4.5745
Max Act: 4.3245. Min Act: -0.1700
Data Index: 4084180 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19