Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1734 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8385. Min Act: -0.1700
Data Index: 317862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8385. Min Act: -0.1700
Data Index: 1136581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8385. Min Act: -0.1700
Data Index: 6897766 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8128. Min Act: -0.1700
Data Index: 2371537 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8214. Min Act: -0.1700
Data Index: 6365011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7956. Min Act: -0.1700
Data Index: 1200173 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.8042. Min Act: -0.1700
Data Index: 365444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7956. Min Act: -0.1700
Data Index: 2952220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7956. Min Act: -0.1700
Data Index: 8587095 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7956. Min Act: -0.1700
Data Index: 6442340 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7870. Min Act: -0.1700
Data Index: 7009532 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7956. Min Act: -0.1700
Data Index: 2705396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7870. Min Act: -0.1700
Data Index: 5457343 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7783. Min Act: -0.1700
Data Index: 954886 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7870. Min Act: -0.1699
Data Index: 2935765 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7697. Min Act: -0.1700
Data Index: 832342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7783. Min Act: -0.1700
Data Index: 4967826 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7783. Min Act: -0.1700
Data Index: 1232149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7611. Min Act: -0.1697
Data Index: 496649 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8385. Min Range: -1.8385
Max Act: 1.7783. Min Act: -0.1700
Data Index: 6802455 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19