Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.1032. Min Range: -6.1032
Max Act: 6.1032. Min Act: -0.1700
Data Index: 6320417 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 6.1032. Min Range: -6.1032
Max Act: 6.0165. Min Act: -0.1700
Data Index: 3114454 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.9728. Min Act: -0.1700
Data Index: 6265023 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.9945. Min Act: -0.1700
Data Index: 3131362 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8978. Min Act: -0.1700
Data Index: 451659 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8906. Min Act: -0.1700
Data Index: 604539 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8212. Min Act: -0.1700
Data Index: 3316508 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8351. Min Act: -0.1700
Data Index: 6293094 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8027. Min Act: -0.1700
Data Index: 7804926 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8382. Min Act: -0.1700
Data Index: 1640234 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8293. Min Act: -0.1700
Data Index: 7036284 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7683. Min Act: -0.1700
Data Index: 1847242 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.8014. Min Act: -0.1700
Data Index: 133552 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7718. Min Act: -0.1700
Data Index: 4829574 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7113. Min Act: -0.1700
Data Index: 3398583 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7267. Min Act: -0.1700
Data Index: 3970905 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7790. Min Act: -0.1700
Data Index: 4219131 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7621. Min Act: -0.1700
Data Index: 4897194 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7719. Min Act: -0.1700
Data Index: 7562380 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 6.1032. Min Range: -6.1032
Max Act: 5.7598. Min Act: -0.1700
Data Index: 3982221 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full textTruncated
Full Text #19