Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.5459. Min Act: -0.1700
Data Index: 5477239 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.4834. Min Act: -0.1700
Data Index: 2523672 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.3897. Min Act: -0.1700
Data Index: 2717657 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.3897. Min Act: -0.1700
Data Index: 994710 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1709. Min Act: -0.1700
Data Index: 7059422 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1397. Min Act: -0.1700
Data Index: 3444220 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1397. Min Act: -0.1700
Data Index: 2107569 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5627493 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1084. Min Act: -0.1700
Data Index: 5329620 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1084. Min Act: -0.1700
Data Index: 4299573 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.1084. Min Act: -0.1700
Data Index: 3613993 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0772. Min Act: -0.1700
Data Index: 3971845 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0147. Min Act: -0.1700
Data Index: 8192022 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0147. Min Act: -0.1700
Data Index: 8354903 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5273903 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0147. Min Act: -0.1700
Data Index: 4527299 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5459. Min Range: -5.5459
Max Act: 4.9834. Min Act: -0.1700
Data Index: 1700996 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5459. Min Range: -5.5459
Max Act: 5.0147. Min Act: -0.1700
Data Index: 4832889 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5459. Min Range: -5.5459
Max Act: 4.9834. Min Act: -0.1700
Data Index: 7450447 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5459. Min Range: -5.5459
Max Act: 4.9834. Min Act: -0.1700
Data Index: 899467 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19