Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.3424. Min Act: -0.1700
Data Index: 2153727 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.3112. Min Act: -0.1700
Data Index: 4805119 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.3112. Min Act: -0.1700
Data Index: 1055793 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.2799. Min Act: -0.1700
Data Index: 7799018 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.2799. Min Act: -0.1700
Data Index: 8284588 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.2799. Min Act: -0.1700
Data Index: 4206728 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4952975 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.2174. Min Act: -0.1700
Data Index: 8290868 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 7499857 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3449900 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6431096 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 2108579 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3896065 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1862. Min Act: -0.1700
Data Index: 2482348 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1549. Min Act: -0.1700
Data Index: 6120681 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1549. Min Act: -0.1700
Data Index: 2003358 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1237. Min Act: -0.1700
Data Index: 2102633 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1237. Min Act: -0.1700
Data Index: 6777187 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1237. Min Act: -0.1700
Data Index: 7029397 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3424. Min Range: -5.3424
Max Act: 5.1237. Min Act: -0.1700
Data Index: 7197967 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19