Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0104. Min Range: -13.0104
Max Act: 13.0104. Min Act: -0.1700
Data Index: 50695 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.9479. Min Act: -0.1700
Data Index: 7195492 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.8854. Min Act: -0.1700
Data Index: 8159121 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.8854. Min Act: -0.1700
Data Index: 5868072 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.8229. Min Act: -0.1700
Data Index: 3829759 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.7604. Min Act: -0.1700
Data Index: 6024237 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.7604. Min Act: -0.1699
Data Index: 5956971 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6979. Min Act: -0.1700
Data Index: 1305137 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6979. Min Act: -0.1700
Data Index: 248577 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6979. Min Act: -0.1700
Data Index: 3859751 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6354. Min Act: -0.1700
Data Index: 6966127 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6354. Min Act: -0.1699
Data Index: 5080753 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6354. Min Act: -0.1700
Data Index: 5525706 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.6354. Min Act: -0.1700
Data Index: 319777 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.5729. Min Act: -0.1700
Data Index: 2236008 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.5104. Min Act: -0.1700
Data Index: 6083512 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.5104. Min Act: -0.1700
Data Index: 3866435 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.5104. Min Act: -0.1700
Data Index: 5894793 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.3854. Min Act: -0.1700
Data Index: 3150495 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0104. Min Range: -13.0104
Max Act: 12.4479. Min Act: -0.1700
Data Index: 3755500 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19