Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0878. Min Range: -4.0878
Max Act: 4.0878. Min Act: -0.1700
Data Index: 5867078 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0878. Min Range: -4.0878
Max Act: 4.0253. Min Act: -0.1700
Data Index: 2168903 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0878. Min Range: -4.0878
Max Act: 4.0253. Min Act: -0.1700
Data Index: 8118576 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9941. Min Act: -0.1700
Data Index: 5723595 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9941. Min Act: -0.1700
Data Index: 2006910 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9941. Min Act: -0.1700
Data Index: 4242636 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9628. Min Act: -0.1700
Data Index: 3241283 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9628. Min Act: -0.1700
Data Index: 448880 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9628. Min Act: -0.1700
Data Index: 5941943 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 8326554 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9315. Min Act: -0.1700
Data Index: 7567701 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 3738931 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 6214187 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 6492788 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 4456307 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 3725521 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.8690. Min Act: -0.1700
Data Index: 4545964 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 5400989 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 5664519 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0878. Min Range: -4.0878
Max Act: 3.9003. Min Act: -0.1700
Data Index: 4007351 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19