Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.8744. Min Act: -0.1700
Data Index: 2622028 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.8268. Min Act: -0.1700
Data Index: 4191753 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.8268. Min Act: -0.1700
Data Index: 5002350 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.8109. Min Act: -0.1700
Data Index: 7894304 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7790. Min Act: -0.1700
Data Index: 8053985 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7471. Min Act: -0.1700
Data Index: 8758396 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7471. Min Act: -0.1700
Data Index: 7567367 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7471. Min Act: -0.1700
Data Index: 6940610 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7471. Min Act: -0.1700
Data Index: 4293620 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6992. Min Act: -0.1700
Data Index: 4293643 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6992. Min Act: -0.1700
Data Index: 4293627 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.7152. Min Act: -0.1700
Data Index: 4191739 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6992. Min Act: -0.1700
Data Index: 8593926 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6992. Min Act: -0.1700
Data Index: 4293636 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6831. Min Act: -0.1700
Data Index: 6574225 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6511. Min Act: -0.1700
Data Index: 4293650 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6511. Min Act: -0.1700
Data Index: 230243 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6511. Min Act: -0.1700
Data Index: 2175904 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6511. Min Act: -0.1700
Data Index: 4381932 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8744. Min Range: -2.8744
Max Act: 2.6671. Min Act: -0.1700
Data Index: 8057592 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19