Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.8667. Min Act: -0.1700
Data Index: 5015866 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.8354. Min Act: -0.1700
Data Index: 7903223 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.8354. Min Act: -0.1700
Data Index: 2388940 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7729. Min Act: -0.1700
Data Index: 2388939 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7729. Min Act: -0.1700
Data Index: 3457871 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7417. Min Act: -0.1700
Data Index: 6438975 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 7903222 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 3986607 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2283246 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6479. Min Act: -0.1700
Data Index: 3986599 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6479. Min Act: -0.1700
Data Index: 452548 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6479. Min Act: -0.1700
Data Index: 4334035 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6479. Min Act: -0.1700
Data Index: 3713849 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1042761 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 5258917 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3947724 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3713848 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.6167. Min Act: -0.1700
Data Index: 2283245 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5542. Min Act: -0.1700
Data Index: 5418373 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8667. Min Range: -4.8667
Max Act: 4.5542. Min Act: -0.1700
Data Index: 6245290 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19