Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.8485. Min Act: -0.1700
Data Index: 5554455 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.7514. Min Act: -0.1700
Data Index: 7025037 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.5928. Min Act: -0.1700
Data Index: 3946203 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.5627. Min Act: -0.1700
Data Index: 8386657 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.5840. Min Act: -0.1700
Data Index: 7183561 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 8232798 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4538. Min Act: -0.1700
Data Index: 3245117 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4840. Min Act: -0.1700
Data Index: 4378711 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4544. Min Act: -0.1700
Data Index: 809348 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4604. Min Act: -0.1700
Data Index: 7442767 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4855. Min Act: -0.1700
Data Index: 2461701 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4735. Min Act: -0.1700
Data Index: 2598148 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4522. Min Act: -0.1700
Data Index: 2985136 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4383. Min Act: -0.1700
Data Index: 1917629 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4118. Min Act: -0.1700
Data Index: 2072071 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4000. Min Act: -0.1700
Data Index: 2686402 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.3874. Min Act: -0.1700
Data Index: 3094958 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4420. Min Act: -0.1700
Data Index: 8314181 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4264. Min Act: -0.1700
Data Index: 591917 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 5.8485. Min Range: -5.8485
Max Act: 5.4357. Min Act: -0.1700
Data Index: 4255477 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full textTruncated
Full Text #19