Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4798. Min Act: -0.1700
Data Index: 927992 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 3285496 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 6205088 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 6579908 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 3835271 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3236. Min Act: -0.1700
Data Index: 6663921 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 503079 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1660369 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 3403143 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 7660023 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 7566547 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 1022734 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 3879526 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1527096 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 5451276 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 7659005 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 3710701 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 5782846 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 4630908 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 2651146 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19