Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.9219. Min Act: -0.1700
Data Index: 978894 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.3282. Min Act: -0.1700
Data Index: 6105845 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2344. Min Act: -0.1700
Data Index: 6105846 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2032. Min Act: -0.1700
Data Index: 1750566 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2032. Min Act: -0.1700
Data Index: 8136990 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2344. Min Act: -0.1700
Data Index: 1940122 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2032. Min Act: -0.1700
Data Index: 157624 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.2344. Min Act: -0.1700
Data Index: 6105847 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1719. Min Act: -0.1700
Data Index: 3249357 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1719. Min Act: -0.1700
Data Index: 6906607 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1719. Min Act: -0.1700
Data Index: 6000983 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1407. Min Act: -0.1700
Data Index: 912472 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1094. Min Act: -0.1700
Data Index: 7289107 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.1094. Min Act: -0.1700
Data Index: 5392434 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5677154 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0157. Min Act: -0.1700
Data Index: 8390751 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 8760746 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 2580537 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 8492547 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9219. Min Range: -6.9219
Max Act: 6.0157. Min Act: -0.1700
Data Index: 3398333 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19