Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2255. Min Range: -6.2255
Max Act: 6.2255. Min Act: -0.1700
Data Index: 113507 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2255. Min Range: -6.2255
Max Act: 6.1630. Min Act: -0.1700
Data Index: 4341766 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2255. Min Range: -6.2255
Max Act: 6.0068. Min Act: -0.1700
Data Index: 3985193 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.8505. Min Act: -0.1700
Data Index: 1885514 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.6005. Min Act: -0.1700
Data Index: 7942458 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5693. Min Act: -0.1700
Data Index: 4792711 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5693. Min Act: -0.1700
Data Index: 7952773 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.6005. Min Act: -0.1700
Data Index: 896498 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.6005. Min Act: -0.1700
Data Index: 6587043 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 6039756 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5068. Min Act: -0.1700
Data Index: 1757821 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 5179490 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 3062514 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 4382066 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 182192 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5380. Min Act: -0.1700
Data Index: 5895580 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5068. Min Act: -0.1700
Data Index: 2814031 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.5068. Min Act: -0.1700
Data Index: 8745630 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.4755. Min Act: -0.1700
Data Index: 6790465 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2255. Min Range: -6.2255
Max Act: 5.4755. Min Act: -0.1700
Data Index: 8418598 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19