Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.7479. Min Act: -0.1700
Data Index: 2827698 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.7181. Min Act: -0.1700
Data Index: 426262 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.7145. Min Act: -0.1700
Data Index: 638290 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6982. Min Act: -0.1700
Data Index: 3208095 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6606. Min Act: -0.1700
Data Index: 69558 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6541. Min Act: -0.1700
Data Index: 3770263 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6595. Min Act: -0.1700
Data Index: 6627580 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6271. Min Act: -0.1700
Data Index: 7374228 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6164. Min Act: -0.1700
Data Index: 5736138 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6175. Min Act: -0.1700
Data Index: 2627142 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6139. Min Act: -0.1700
Data Index: 6632560 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6168. Min Act: -0.1700
Data Index: 5310408 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6180. Min Act: -0.1700
Data Index: 6566598 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5951. Min Act: -0.1700
Data Index: 1968401 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5990. Min Act: -0.1700
Data Index: 3701487 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5810. Min Act: -0.1700
Data Index: 1616839 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5895. Min Act: -0.1700
Data Index: 429948 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5912. Min Act: -0.1700
Data Index: 5114926 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5812. Min Act: -0.1700
Data Index: 1817036 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5836. Min Act: -0.1700
Data Index: 1197547 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full textTruncated
Full Text #19