Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.6334. Min Act: -0.1700
Data Index: 4616802 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.2896. Min Act: -0.1700
Data Index: 5362477 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.2584. Min Act: -0.1700
Data Index: 4616803 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1959. Min Act: -0.1700
Data Index: 6085191 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3453117 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1959. Min Act: -0.1700
Data Index: 1204869 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 460903 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 4986885 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 4471158 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 6233185 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 7243425 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.1021. Min Act: -0.1700
Data Index: 7205192 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 5751581 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2402932 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 1064371 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0396. Min Act: -0.1700
Data Index: 895695 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0396. Min Act: -0.1700
Data Index: 8126116 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 6800457 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0396. Min Act: -0.1700
Data Index: 3289405 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6334. Min Range: -6.6334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 261442 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19