Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.6354. Min Act: -0.1700
Data Index: 1482263 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.5415. Min Act: -0.1700
Data Index: 2278789 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.4475. Min Act: -0.1700
Data Index: 842838 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.4475. Min Act: -0.1700
Data Index: 5087873 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.4005. Min Act: -0.1700
Data Index: 5314422 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3691. Min Act: -0.1700
Data Index: 7629270 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3691. Min Act: -0.1700
Data Index: 336911 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3221. Min Act: -0.1700
Data Index: 7957528 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3378. Min Act: -0.1700
Data Index: 411631 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3534. Min Act: -0.1700
Data Index: 8499429 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3064. Min Act: -0.1700
Data Index: 5388246 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3221. Min Act: -0.1700
Data Index: 3494510 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3064. Min Act: -0.1700
Data Index: 565053 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3221. Min Act: -0.1700
Data Index: 2115828 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3064. Min Act: -0.1700
Data Index: 4961606 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3221. Min Act: -0.1700
Data Index: 3907848 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.2907. Min Act: -0.1700
Data Index: 8066251 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.3534. Min Act: -0.1700
Data Index: 6479890 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.2907. Min Act: -0.1700
Data Index: 4011011 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6354. Min Range: -3.6354
Max Act: 3.2750. Min Act: -0.1700
Data Index: 2551187 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19