Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.4798. Min Act: -0.1700
Data Index: 8643182 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.4486. Min Act: -0.1700
Data Index: 4111446 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.3548. Min Act: -0.1700
Data Index: 5211766 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.3548. Min Act: -0.1700
Data Index: 4596025 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2923. Min Act: -0.1700
Data Index: 6958625 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.3236. Min Act: -0.1700
Data Index: 3302120 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2923. Min Act: -0.1700
Data Index: 6586767 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2611. Min Act: -0.1700
Data Index: 3737701 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2611. Min Act: -0.1700
Data Index: 8324626 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2298. Min Act: -0.1700
Data Index: 5932224 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2298. Min Act: -0.1700
Data Index: 1466074 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.2298. Min Act: -0.1700
Data Index: 889335 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1986. Min Act: -0.1700
Data Index: 7102365 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1986. Min Act: -0.1700
Data Index: 4736020 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1986. Min Act: -0.1700
Data Index: 375454 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1986. Min Act: -0.1700
Data Index: 795215 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1673. Min Act: -0.1700
Data Index: 5202810 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1673. Min Act: -0.1700
Data Index: 5176384 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1361. Min Act: -0.1700
Data Index: 830708 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4798. Min Range: -7.4798
Max Act: 7.1361. Min Act: -0.1700
Data Index: 5421610 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19