Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.9685. Min Act: -0.1700
Data Index: 8152412 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.8748. Min Act: -0.1700
Data Index: 5473125 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3292018 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7810. Min Act: -0.1700
Data Index: 8527844 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7498. Min Act: -0.1700
Data Index: 5865290 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7498. Min Act: -0.1700
Data Index: 3878178 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7498. Min Act: -0.1700
Data Index: 740057 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7498. Min Act: -0.1699
Data Index: 4279478 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1700
Data Index: 4996448 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1699
Data Index: 4878000 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6176732 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6113581 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1700
Data Index: 8649465 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1700
Data Index: 350966 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.6873. Min Act: -0.1700
Data Index: 279138 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.6873. Min Act: -0.1700
Data Index: 6004857 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.6873. Min Act: -0.1700
Data Index: 3111469 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.6873. Min Act: -0.1700
Data Index: 2006478 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.7185. Min Act: -0.1696
Data Index: 6240511 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9685. Min Range: -5.9685
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1539509 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19