Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4060. Min Range: -6.4060
Max Act: 6.4060. Min Act: -0.1700
Data Index: 158793 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4060. Min Range: -6.4060
Max Act: 6.3123. Min Act: -0.1700
Data Index: 249153 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4060. Min Range: -6.4060
Max Act: 6.3123. Min Act: -0.1700
Data Index: 283907 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4060. Min Range: -6.4060
Max Act: 6.2185. Min Act: -0.1700
Data Index: 7190004 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4060. Min Range: -6.4060
Max Act: 6.1248. Min Act: -0.1700
Data Index: 6173751 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.9373. Min Act: -0.1700
Data Index: 7556381 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.8435. Min Act: -0.1700
Data Index: 2216850 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.8748. Min Act: -0.1700
Data Index: 5927331 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.8435. Min Act: -0.1700
Data Index: 3318528 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.8123. Min Act: -0.1700
Data Index: 520533 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7810. Min Act: -0.1700
Data Index: 5037336 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7498. Min Act: -0.1700
Data Index: 5448571 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7498. Min Act: -0.1700
Data Index: 6638555 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7498. Min Act: -0.1700
Data Index: 8419026 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7185. Min Act: -0.1700
Data Index: 1813869 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.7185. Min Act: -0.1700
Data Index: 7291084 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5601498 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.6873. Min Act: -0.1700
Data Index: 2995259 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.6873. Min Act: -0.1700
Data Index: 1352980 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4060. Min Range: -6.4060
Max Act: 5.6873. Min Act: -0.1700
Data Index: 8457380 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19