Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0325. Min Range: -2.0325
Max Act: 2.0325. Min Act: -0.1700
Data Index: 143924 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9734. Min Act: -0.1700
Data Index: 8415829 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9479. Min Act: -0.1651
Data Index: 2752312 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9479. Min Act: -0.1695
Data Index: 4833009 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9479. Min Act: -0.1700
Data Index: 2336859 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9309. Min Act: -0.1699
Data Index: 1399840 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9309. Min Act: -0.1662
Data Index: 7477522 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9224. Min Act: -0.1700
Data Index: 3744046 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9139. Min Act: -0.1697
Data Index: 2044550 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8969. Min Act: -0.1700
Data Index: 2570719 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.9054. Min Act: -0.1699
Data Index: 4569519 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1697
Data Index: 1187834 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1698
Data Index: 8226994 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8798. Min Act: -0.1651
Data Index: 312039 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1700
Data Index: 3329133 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1698
Data Index: 3197360 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1699
Data Index: 6386964 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8712. Min Act: -0.1657
Data Index: 2520999 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8798. Min Act: -0.1649
Data Index: 3569177 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0325. Min Range: -2.0325
Max Act: 1.8883. Min Act: -0.1700
Data Index: 6283689 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19