Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4213 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 7685489 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.4826. Min Act: -0.1700
Data Index: 7678248 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.2013. Min Act: -0.1700
Data Index: 3412801 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1701. Min Act: -0.1700
Data Index: 4305593 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1701. Min Act: -0.1700
Data Index: 477285 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1388. Min Act: -0.1700
Data Index: 5053830 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1701. Min Act: -0.1699
Data Index: 3369852 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 905921 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 3880427 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 3460491 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 874907 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 2554639 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.1076. Min Act: -0.1700
Data Index: 8411429 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0451. Min Act: -0.1700
Data Index: 6513988 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0451. Min Act: -0.1700
Data Index: 6236838 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0451. Min Act: -0.1700
Data Index: 5679288 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5763. Min Range: -6.5763
Max Act: 5.9826. Min Act: -0.1700
Data Index: 3487759 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0451. Min Act: -0.1700
Data Index: 3188611 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5763. Min Range: -6.5763
Max Act: 6.0138. Min Act: -0.1700
Data Index: 4930956 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5763. Min Range: -6.5763
Max Act: 5.9826. Min Act: -0.1700
Data Index: 2567391 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19