Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.1209. Min Act: -0.1700
Data Index: 427865 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.1209. Min Act: -0.1700
Data Index: 5681963 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3838827 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.0584. Min Act: -0.1700
Data Index: 1104854 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.0271. Min Act: -0.1700
Data Index: 72066 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9959. Min Act: -0.1700
Data Index: 2247014 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9959. Min Act: -0.1700
Data Index: 2467888 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9646. Min Act: -0.1700
Data Index: 2635180 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9646. Min Act: -0.1700
Data Index: 887366 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9334. Min Act: -0.1700
Data Index: 4838758 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9021. Min Act: -0.1700
Data Index: 2655714 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9021. Min Act: -0.1700
Data Index: 7547663 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9021. Min Act: -0.1700
Data Index: 814525 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9021. Min Act: -0.1700
Data Index: 427864 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8709. Min Act: -0.1700
Data Index: 4210763 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8709. Min Act: -0.1700
Data Index: 8747168 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8084. Min Act: -0.1700
Data Index: 2451741 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8084. Min Act: -0.1700
Data Index: 6675140 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 7385685 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 4925507 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19