Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.9678. Min Act: -0.1700
Data Index: 1182678 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.8428. Min Act: -0.1700
Data Index: 784741 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.8115. Min Act: -0.1700
Data Index: 7388708 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4642924 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7178. Min Act: -0.1700
Data Index: 3460255 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7178. Min Act: -0.1700
Data Index: 69761 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6865. Min Act: -0.1700
Data Index: 4891636 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6865. Min Act: -0.1700
Data Index: 8044598 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6553. Min Act: -0.1700
Data Index: 7379197 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6553. Min Act: -0.1700
Data Index: 2975377 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6865. Min Act: -0.1700
Data Index: 6516560 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6553. Min Act: -0.1700
Data Index: 4298512 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4901892 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 8634667 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 7621255 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 5367049 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 2253351 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.5928. Min Act: -0.1700
Data Index: 440194 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.5928. Min Act: -0.1700
Data Index: 6196362 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.5928. Min Act: -0.1700
Data Index: 2800846 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19