Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.8567. Min Act: -0.1700
Data Index: 7080233 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.7317. Min Act: -0.1700
Data Index: 8370998 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6692. Min Act: -0.1700
Data Index: 6011098 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6692. Min Act: -0.1700
Data Index: 806833 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6379. Min Act: -0.1700
Data Index: 882723 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6379. Min Act: -0.1700
Data Index: 4330954 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6529850 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 507431 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 4141655 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 5818374 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6548014 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5754. Min Act: -0.1700
Data Index: 5182303 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5722093 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7360716 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5260356 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 59825 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 1594332 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 2587883 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 6251855 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 634177 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19