Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1174. Min Range: -8.1174
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4604916 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.3986. Min Act: -0.1700
Data Index: 7391365 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.3674. Min Act: -0.1700
Data Index: 2132152 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.2736. Min Act: -0.1700
Data Index: 5533664 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.1486. Min Act: -0.1700
Data Index: 2752256 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.2111. Min Act: -0.1700
Data Index: 2802853 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.1799. Min Act: -0.1700
Data Index: 4604917 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.0861. Min Act: -0.1700
Data Index: 2752252 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.0861. Min Act: -0.1700
Data Index: 411574 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.0861. Min Act: -0.1700
Data Index: 786080 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1174. Min Range: -8.1174
Max Act: 7.0236. Min Act: -0.1700
Data Index: 954329 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.9611. Min Act: -0.1700
Data Index: 232042 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.9299. Min Act: -0.1700
Data Index: 4673019 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8986. Min Act: -0.1700
Data Index: 5155803 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8986. Min Act: -0.1700
Data Index: 4171806 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8986. Min Act: -0.1700
Data Index: 411573 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8049. Min Act: -0.1700
Data Index: 5701921 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8986. Min Act: -0.1700
Data Index: 7868605 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.8674. Min Act: -0.1700
Data Index: 8698134 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1174. Min Range: -8.1174
Max Act: 6.9299. Min Act: -0.1700
Data Index: 1437321 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19