Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.0556. Min Range: -7.0556
Max Act: 7.0556. Min Act: -0.1700
Data Index: 4936277 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.6872. Min Act: -0.1700
Data Index: 779020 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.6039. Min Act: -0.1700
Data Index: 6448602 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.6051. Min Act: -0.1700
Data Index: 7776354 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.6146. Min Act: -0.1700
Data Index: 5800329 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.6115. Min Act: -0.1700
Data Index: 1193440 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5325. Min Act: -0.1700
Data Index: 7657845 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5948. Min Act: -0.1700
Data Index: 5262042 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5497. Min Act: -0.1700
Data Index: 5800330 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5446. Min Act: -0.1700
Data Index: 6995384 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5714. Min Act: -0.1700
Data Index: 565386 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5736. Min Act: -0.1700
Data Index: 6474035 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5331. Min Act: -0.1700
Data Index: 3591146 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5643. Min Act: -0.1700
Data Index: 2540305 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5566. Min Act: -0.1700
Data Index: 3252132 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5514. Min Act: -0.1700
Data Index: 4778264 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.4979. Min Act: -0.1700
Data Index: 6777642 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5169. Min Act: -0.1700
Data Index: 7615896 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5315. Min Act: -0.1700
Data Index: 5405613 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 7.0556. Min Range: -7.0556
Max Act: 6.5395. Min Act: -0.1700
Data Index: 5593192 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full textTruncated
Full Text #19