Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5648 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.7397. Min Act: -0.1700
Data Index: 3997939 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.6147. Min Act: -0.1700
Data Index: 6486561 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.5522. Min Act: -0.1700
Data Index: 4121612 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.3959. Min Act: -0.1700
Data Index: 3718497 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.3959. Min Act: -0.1700
Data Index: 6696532 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.3647. Min Act: -0.1700
Data Index: 5249691 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2709. Min Act: -0.1700
Data Index: 7934398 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2709. Min Act: -0.1700
Data Index: 2329320 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2709. Min Act: -0.1700
Data Index: 1491319 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2397. Min Act: -0.1700
Data Index: 8063897 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2397. Min Act: -0.1700
Data Index: 1709492 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2397. Min Act: -0.1700
Data Index: 2363085 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2084. Min Act: -0.1700
Data Index: 6827805 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2084. Min Act: -0.1700
Data Index: 5258506 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2084. Min Act: -0.1700
Data Index: 1451924 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2084. Min Act: -0.1700
Data Index: 1309084 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.2084. Min Act: -0.1700
Data Index: 1519761 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.1459. Min Act: -0.1700
Data Index: 6694008 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.1459. Min Act: -0.1700
Data Index: 5978444 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7397. Min Range: -5.7397
Max Act: 5.1772. Min Act: -0.1700
Data Index: 4295481 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19