Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1556. Min Range: -7.1556
Max Act: 7.1556. Min Act: -0.1700
Data Index: 1351086 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1556. Min Range: -7.1556
Max Act: 7.1556. Min Act: -0.1700
Data Index: 1831402 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1556. Min Range: -7.1556
Max Act: 7.0931. Min Act: -0.1700
Data Index: 6843699 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.6244. Min Act: -0.1700
Data Index: 864156 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.5931. Min Act: -0.1700
Data Index: 1428244 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.5619. Min Act: -0.1700
Data Index: 3446839 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.5306. Min Act: -0.1700
Data Index: 5791157 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.4369. Min Act: -0.1700
Data Index: 4044193 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.4369. Min Act: -0.1700
Data Index: 4577381 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3744. Min Act: -0.1700
Data Index: 2303418 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3744. Min Act: -0.1700
Data Index: 2847742 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3744. Min Act: -0.1700
Data Index: 4355661 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3119. Min Act: -0.1700
Data Index: 1964005 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3431. Min Act: -0.1700
Data Index: 3686862 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3431. Min Act: -0.1700
Data Index: 8247309 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3119. Min Act: -0.1700
Data Index: 83270 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3119. Min Act: -0.1700
Data Index: 224151 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3119. Min Act: -0.1700
Data Index: 2845422 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.3119. Min Act: -0.1700
Data Index: 7682184 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1556. Min Range: -7.1556
Max Act: 6.2806. Min Act: -0.1700
Data Index: 4805336 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19