Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3785. Min Act: -0.1700
Data Index: 7616001 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3160. Min Act: -0.1700
Data Index: 2674720 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2848. Min Act: -0.1700
Data Index: 910594 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2848. Min Act: -0.1700
Data Index: 6256416 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2848. Min Act: -0.1700
Data Index: 1058225 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 325507 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 978772 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 944135 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2223. Min Act: -0.1700
Data Index: 6435259 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2223. Min Act: -0.1700
Data Index: 6355662 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 3589063 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 8341746 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 1529756 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 25259 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1598. Min Act: -0.1700
Data Index: 7178000 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1598. Min Act: -0.1700
Data Index: 1754528 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 1940200 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 5603624 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0973. Min Act: -0.1700
Data Index: 710232 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0973. Min Act: -0.1700
Data Index: 4058208 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19