Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0823. Min Act: -0.1700
Data Index: 4192652 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0508. Min Act: -0.1700
Data Index: 7412165 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0192. Min Act: -0.1700
Data Index: 2258803 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0192. Min Act: -0.1700
Data Index: 5169908 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0034. Min Act: -0.1700
Data Index: 107967 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0192. Min Act: -0.1700
Data Index: 3246596 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0034. Min Act: -0.1700
Data Index: 5652021 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0823. Min Range: -3.0823
Max Act: 3.0192. Min Act: -0.1700
Data Index: 6469510 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9560. Min Act: -0.1700
Data Index: 2993231 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9401. Min Act: -0.1700
Data Index: 8332210 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9876. Min Act: -0.1700
Data Index: 483838 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9718. Min Act: -0.1700
Data Index: 7477017 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9718. Min Act: -0.1700
Data Index: 2617192 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9718. Min Act: -0.1700
Data Index: 8291006 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9560. Min Act: -0.1700
Data Index: 4559111 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9560. Min Act: -0.1700
Data Index: 6952964 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9718. Min Act: -0.1700
Data Index: 4779091 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9401. Min Act: -0.1700
Data Index: 1123430 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9401. Min Act: -0.1700
Data Index: 2832432 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0823. Min Range: -3.0823
Max Act: 2.9560. Min Act: -0.1700
Data Index: 2746274 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19