Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.2509. Min Act: -0.1700
Data Index: 3936235 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.2674. Min Act: -0.1700
Data Index: 3602849 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.2509. Min Act: -0.1700
Data Index: 3887469 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.2343. Min Act: -0.1700
Data Index: 3496045 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1680. Min Act: -0.1700
Data Index: 7526965 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1680. Min Act: -0.1700
Data Index: 4950850 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1513. Min Act: -0.1700
Data Index: 4308917 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1513. Min Act: -0.1700
Data Index: 4778909 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1513. Min Act: -0.1700
Data Index: 3397892 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1513. Min Act: -0.1700
Data Index: 1734546 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1513. Min Act: -0.1700
Data Index: 6761293 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1346. Min Act: -0.1700
Data Index: 374569 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1179. Min Act: -0.1700
Data Index: 2895755 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1179. Min Act: -0.1700
Data Index: 8659165 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1179. Min Act: -0.1700
Data Index: 8477668 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1012. Min Act: -0.1700
Data Index: 3378027 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1179. Min Act: -0.1700
Data Index: 368612 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1346. Min Act: -0.1700
Data Index: 5440118 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1179. Min Act: -0.1700
Data Index: 6250972 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2674. Min Range: -2.2674
Max Act: 2.1012. Min Act: -0.1700
Data Index: 1837156 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19