Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.6111. Min Act: -0.1700
Data Index: 165417 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.4236. Min Act: -0.1700
Data Index: 4112660 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.2361. Min Act: -0.1700
Data Index: 390491 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.2048. Min Act: -0.1700
Data Index: 963983 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.2048. Min Act: -0.1700
Data Index: 390492 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.1111. Min Act: -0.1700
Data Index: 5988716 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.0798. Min Act: -0.1700
Data Index: 4638891 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.0486. Min Act: -0.1700
Data Index: 5988712 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6111. Min Range: -7.6111
Max Act: 7.0173. Min Act: -0.1700
Data Index: 96305 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.9236. Min Act: -0.1700
Data Index: 5400106 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.9236. Min Act: -0.1700
Data Index: 3183855 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.8923. Min Act: -0.1700
Data Index: 2707350 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.8298. Min Act: -0.1700
Data Index: 6040608 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.8298. Min Act: -0.1700
Data Index: 4559183 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.7986. Min Act: -0.1700
Data Index: 3806454 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.7986. Min Act: -0.1700
Data Index: 6063832 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.7048. Min Act: -0.1700
Data Index: 1686506 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.7048. Min Act: -0.1700
Data Index: 4683515 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.7048. Min Act: -0.1700
Data Index: 7700362 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6111. Min Range: -7.6111
Max Act: 6.6736. Min Act: -0.1700
Data Index: 5742723 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19