Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0243. Min Range: -6.0243
Max Act: 6.0243. Min Act: -0.1700
Data Index: 8409860 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.9930. Min Act: -0.1700
Data Index: 5107774 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.8368. Min Act: -0.1700
Data Index: 6619230 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.8055. Min Act: -0.1700
Data Index: 3305027 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7743. Min Act: -0.1700
Data Index: 3770776 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7430. Min Act: -0.1700
Data Index: 3446447 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7118. Min Act: -0.1700
Data Index: 6744513 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7118. Min Act: -0.1700
Data Index: 2956547 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7118. Min Act: -0.1700
Data Index: 3737877 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6805. Min Act: -0.1700
Data Index: 8386413 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.7118. Min Act: -0.1700
Data Index: 4098889 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1690246 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6180. Min Act: -0.1700
Data Index: 1511755 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1961052 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6180. Min Act: -0.1700
Data Index: 3026189 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6493. Min Act: -0.1700
Data Index: 7679049 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6180. Min Act: -0.1700
Data Index: 1246826 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6180. Min Act: -0.1700
Data Index: 6732913 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1987449 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0243. Min Range: -6.0243
Max Act: 5.6180. Min Act: -0.1700
Data Index: 2839272 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19