Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.9332. Min Act: -0.1700
Data Index: 7549872 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.9161. Min Act: -0.1700
Data Index: 4476447 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.9161. Min Act: -0.1700
Data Index: 4962722 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.9161. Min Act: -0.1700
Data Index: 760071 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.9332. Min Act: -0.1700
Data Index: 2383825 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8991. Min Act: -0.1700
Data Index: 3952462 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8820. Min Act: -0.1700
Data Index: 5053186 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8649. Min Act: -0.1700
Data Index: 876133 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8478. Min Act: -0.1700
Data Index: 4261993 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8478. Min Act: -0.1700
Data Index: 8388869 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8649. Min Act: -0.1700
Data Index: 5691119 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8478. Min Act: -0.1700
Data Index: 6926003 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8478. Min Act: -0.1700
Data Index: 588541 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8307. Min Act: -0.1700
Data Index: 525137 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8307. Min Act: -0.1700
Data Index: 1200784 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8478. Min Act: -0.1700
Data Index: 678051 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8307. Min Act: -0.1700
Data Index: 5338438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8135. Min Act: -0.1700
Data Index: 5722892 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8135. Min Act: -0.1700
Data Index: 2399897 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9332. Min Range: -1.9332
Max Act: 1.8135. Min Act: -0.1700
Data Index: 6756450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19