Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.6459. Min Act: -0.1700
Data Index: 6396200 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.4584. Min Act: -0.1700
Data Index: 6021102 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.4584. Min Act: -0.1700
Data Index: 7583917 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3959. Min Act: -0.1700
Data Index: 8374382 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3959. Min Act: -0.1700
Data Index: 8594473 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3959. Min Act: -0.1700
Data Index: 3641694 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3334. Min Act: -0.1700
Data Index: 72111 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3334. Min Act: -0.1700
Data Index: 3130928 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3334. Min Act: -0.1700
Data Index: 5754605 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3959. Min Act: -0.1700
Data Index: 8245530 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3334. Min Act: -0.1700
Data Index: 3240489 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.3334. Min Act: -0.1700
Data Index: 1503988 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2709. Min Act: -0.1700
Data Index: 7017484 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2709. Min Act: -0.1700
Data Index: 8832582 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2084. Min Act: -0.1700
Data Index: 2253724 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2084. Min Act: -0.1700
Data Index: 2800819 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2709. Min Act: -0.1700
Data Index: 8427300 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2084. Min Act: -0.1700
Data Index: 6262163 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2084. Min Act: -0.1700
Data Index: 6019472 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6459. Min Range: -10.6459
Max Act: 10.2084. Min Act: -0.1700
Data Index: 2446722 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19