Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.5258. Min Act: -0.1700
Data Index: 1283343 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.4321. Min Act: -0.1700
Data Index: 5098352 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.4008. Min Act: -0.1700
Data Index: 5188231 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.3071. Min Act: -0.1700
Data Index: 5460120 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.3071. Min Act: -0.1700
Data Index: 1813164 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.2446. Min Act: -0.1700
Data Index: 7086235 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1821. Min Act: -0.1700
Data Index: 7931213 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1821. Min Act: -0.1700
Data Index: 7739132 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.2133. Min Act: -0.1700
Data Index: 4254551 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 2797740 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3629897 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 3395924 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 2774371 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 8432450 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 6720461 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 3113868 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1508. Min Act: -0.1700
Data Index: 8226121 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.0883. Min Act: -0.1700
Data Index: 3928721 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.1196. Min Act: -0.1700
Data Index: 3911643 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5258. Min Range: -5.5258
Max Act: 5.0571. Min Act: -0.1700
Data Index: 724721 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19