Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8966. Min Act: -0.1700
Data Index: 8364643 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8649. Min Act: -0.1700
Data Index: 4609625 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8649. Min Act: -0.1700
Data Index: 3140847 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8331. Min Act: -0.1700
Data Index: 8308342 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8013. Min Act: -0.1700
Data Index: 3114484 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.8013. Min Act: -0.1700
Data Index: 996886 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.7853. Min Act: -0.1700
Data Index: 3555284 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.7534. Min Act: -0.1700
Data Index: 5110067 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6895. Min Act: -0.1700
Data Index: 5554366 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6735. Min Act: -0.1700
Data Index: 319972 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6895. Min Act: -0.1700
Data Index: 6201662 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6735. Min Act: -0.1700
Data Index: 517128 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6735. Min Act: -0.1700
Data Index: 905936 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6735. Min Act: -0.1700
Data Index: 690307 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6895. Min Act: -0.1700
Data Index: 3353373 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6414. Min Act: -0.1700
Data Index: 3644733 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6574. Min Act: -0.1700
Data Index: 1267590 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6414. Min Act: -0.1700
Data Index: 4359782 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6414. Min Act: -0.1700
Data Index: 278030 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8966. Min Range: -2.8966
Max Act: 2.6253. Min Act: -0.1700
Data Index: 3853110 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19