Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.7356. Min Act: -0.1700
Data Index: 360433 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.7356. Min Act: -0.1700
Data Index: 1442258 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.6731. Min Act: -0.1700
Data Index: 2943638 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.6106. Min Act: -0.1700
Data Index: 6726805 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.4231. Min Act: -0.1700
Data Index: 5912180 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.4231. Min Act: -0.1700
Data Index: 2730363 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.3606. Min Act: -0.1700
Data Index: 8529234 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.3606. Min Act: -0.1700
Data Index: 6375446 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.3606. Min Act: -0.1700
Data Index: 559336 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.2981. Min Act: -0.1700
Data Index: 457431 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.2981. Min Act: -0.1700
Data Index: 2036172 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.1731. Min Act: -0.1700
Data Index: 4577774 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.1106. Min Act: -0.1700
Data Index: 4486089 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.1106. Min Act: -0.1700
Data Index: 4779472 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.1106. Min Act: -0.1700
Data Index: 5297103 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.1106. Min Act: -0.1700
Data Index: 5519671 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 360405 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7356. Min Range: -8.7356
Max Act: 7.9856. Min Act: -0.1700
Data Index: 2352603 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 7203221 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7356. Min Range: -8.7356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 3015897 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19