Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0403. Min Range: -4.0403
Max Act: 4.0403. Min Act: -0.1700
Data Index: 2643481 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.0403. Min Range: -4.0403
Max Act: 4.0219. Min Act: -0.1700
Data Index: 5199933 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.0403. Min Range: -4.0403
Max Act: 4.0114. Min Act: -0.1700
Data Index: 6452674 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9226. Min Act: -0.1700
Data Index: 588896 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9333. Min Act: -0.1700
Data Index: 3910069 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9471. Min Act: -0.1700
Data Index: 3996237 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9090. Min Act: -0.1700
Data Index: 6641410 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9310. Min Act: -0.1700
Data Index: 284550 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9375. Min Act: -0.1700
Data Index: 1692746 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9402. Min Act: -0.1700
Data Index: 452447 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8876. Min Act: -0.1700
Data Index: 6938888 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9238. Min Act: -0.1700
Data Index: 1879045 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9168. Min Act: -0.1700
Data Index: 2317923 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.9029. Min Act: -0.1700
Data Index: 8632968 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8942. Min Act: -0.1700
Data Index: 4745233 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8889. Min Act: -0.1700
Data Index: 8113380 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8637. Min Act: -0.1700
Data Index: 383344 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8577. Min Act: -0.1700
Data Index: 2376798 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8737. Min Act: -0.1700
Data Index: 3802714 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.0403. Min Range: -4.0403
Max Act: 3.8438. Min Act: -0.1700
Data Index: 929033 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full textTruncated
Full Text #19