Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.8386. Min Act: -0.1700
Data Index: 6259203 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.8067. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.6148. Min Act: -0.1700
Data Index: 136707 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5503. Min Act: -0.1700
Data Index: 7484163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5503. Min Act: -0.1700
Data Index: 4500418 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5665. Min Act: -0.1700
Data Index: 851858 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5503. Min Act: -0.1700
Data Index: 792760 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5180. Min Act: -0.1700
Data Index: 3274355 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5180. Min Act: -0.1700
Data Index: 7008119 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4856. Min Act: -0.1700
Data Index: 4264347 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4856. Min Act: -0.1700
Data Index: 6094310 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4856. Min Act: -0.1700
Data Index: 1884225 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.5018. Min Act: -0.1700
Data Index: 5029213 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4694. Min Act: -0.1700
Data Index: 1027725 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4531. Min Act: -0.1700
Data Index: 8585607 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4694. Min Act: -0.1700
Data Index: 1527628 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4369. Min Act: -0.1700
Data Index: 6378525 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4531. Min Act: -0.1700
Data Index: 7083046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4369. Min Act: -0.1700
Data Index: 7622355 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8386. Min Range: -2.8386
Max Act: 2.4206. Min Act: -0.1700
Data Index: 2149941 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19