Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6408. Min Act: -0.1700
Data Index: 8540754 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6431. Min Act: -0.1700
Data Index: 6742364 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6182. Min Act: -0.1700
Data Index: 6697378 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6299. Min Act: -0.1700
Data Index: 612699 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6213. Min Act: -0.1700
Data Index: 785905 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5947. Min Act: -0.1700
Data Index: 3040696 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5888. Min Act: -0.1700
Data Index: 2113335 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5984. Min Act: -0.1700
Data Index: 825107 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.6062. Min Act: -0.1700
Data Index: 100276 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5888. Min Act: -0.1700
Data Index: 8410067 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5843. Min Act: -0.1700
Data Index: 1474799 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5642. Min Act: -0.1700
Data Index: 8778590 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5600. Min Act: -0.1700
Data Index: 1913767 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5645. Min Act: -0.1700
Data Index: 7529432 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5634. Min Act: -0.1700
Data Index: 38529 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5555. Min Act: -0.1700
Data Index: 1492533 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5302. Min Act: -0.1700
Data Index: 5553920 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5415. Min Act: -0.1700
Data Index: 5937731 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5417. Min Act: -0.1700
Data Index: 7129070 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.6431. Min Range: -3.6431
Max Act: 3.5554. Min Act: -0.1700
Data Index: 6057653 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full textTruncated
Full Text #19