Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6345 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.7880. Min Act: -0.1700
Data Index: 1087332 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.5693. Min Act: -0.1700
Data Index: 1776979 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.4755. Min Act: -0.1700
Data Index: 5591407 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.3818. Min Act: -0.1700
Data Index: 6771551 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.3505. Min Act: -0.1700
Data Index: 6844698 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.2880. Min Act: -0.1700
Data Index: 470099 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.2880. Min Act: -0.1700
Data Index: 5329025 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.2880. Min Act: -0.1700
Data Index: 2963682 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1943. Min Act: -0.1700
Data Index: 2847134 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1318. Min Act: -0.1700
Data Index: 5662443 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1318. Min Act: -0.1700
Data Index: 4377539 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1005. Min Act: -0.1700
Data Index: 8667850 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1318. Min Act: -0.1700
Data Index: 22751 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1318. Min Act: -0.1700
Data Index: 233941 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.1005. Min Act: -0.1700
Data Index: 3641831 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.0693. Min Act: -0.1700
Data Index: 5990039 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.0380. Min Act: -0.1700
Data Index: 2527318 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.0380. Min Act: -0.1700
Data Index: 6523659 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.0380. Min Act: -0.1700
Data Index: 7928002 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7880. Min Range: -7.7880
Max Act: 7.0380. Min Act: -0.1700
Data Index: 1372729 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19