Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.9241. Min Act: -0.1700
Data Index: 5111291 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8815. Min Act: -0.1700
Data Index: 5630401 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.9326. Min Act: -0.1700
Data Index: 7089094 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8900. Min Act: -0.1700
Data Index: 6529371 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8815. Min Act: -0.1700
Data Index: 3298948 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8815. Min Act: -0.1700
Data Index: 6751042 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8900. Min Act: -0.1700
Data Index: 7514242 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8644. Min Act: -0.1700
Data Index: 4246250 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8472. Min Act: -0.1700
Data Index: 5963075 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8644. Min Act: -0.1700
Data Index: 3011747 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8558. Min Act: -0.1700
Data Index: 4894794 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8472. Min Act: -0.1700
Data Index: 5912943 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8387. Min Act: -0.1700
Data Index: 6252625 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8644. Min Act: -0.1699
Data Index: 4825869 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8472. Min Act: -0.1700
Data Index: 7932986 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8387. Min Act: -0.1700
Data Index: 1716970 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8129. Min Act: -0.1700
Data Index: 3773137 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8387. Min Act: -0.1700
Data Index: 5503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8472. Min Act: -0.1700
Data Index: 4526320 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9326. Min Range: -1.9326
Max Act: 1.8301. Min Act: -0.1700
Data Index: 1400942 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19