Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1091. Min Range: -8.1091
Max Act: 8.1091. Min Act: -0.1700
Data Index: 5902103 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.9841. Min Act: -0.1700
Data Index: 868377 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.9216. Min Act: -0.1700
Data Index: 1811945 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.9216. Min Act: -0.1700
Data Index: 2212459 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.8591. Min Act: -0.1700
Data Index: 2728983 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.8591. Min Act: -0.1700
Data Index: 4051571 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.7966. Min Act: -0.1700
Data Index: 2072836 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.7966. Min Act: -0.1700
Data Index: 8324529 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.7966. Min Act: -0.1700
Data Index: 721391 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.7966. Min Act: -0.1700
Data Index: 5522490 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.7341. Min Act: -0.1700
Data Index: 4647025 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.6716. Min Act: -0.1700
Data Index: 2346635 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.6404. Min Act: -0.1700
Data Index: 1584658 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.6716. Min Act: -0.1700
Data Index: 319322 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.6091. Min Act: -0.1700
Data Index: 1577829 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.6091. Min Act: -0.1700
Data Index: 718736 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.5154. Min Act: -0.1700
Data Index: 4804657 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.5466. Min Act: -0.1700
Data Index: 429088 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.5154. Min Act: -0.1700
Data Index: 7906167 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1091. Min Range: -8.1091
Max Act: 7.5154. Min Act: -0.1700
Data Index: 1773891 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19