Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.9102. Min Act: -0.1700
Data Index: 553560 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.8477. Min Act: -0.1700
Data Index: 4421541 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.8164. Min Act: -0.1700
Data Index: 115771 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.8164. Min Act: -0.1700
Data Index: 3086608 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.7539. Min Act: -0.1700
Data Index: 2450396 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.7851. Min Act: -0.1700
Data Index: 4276011 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.7226. Min Act: -0.1700
Data Index: 7822065 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6913. Min Act: -0.1700
Data Index: 5491738 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6600. Min Act: -0.1700
Data Index: 4253247 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6913. Min Act: -0.1700
Data Index: 6417013 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6287. Min Act: -0.1700
Data Index: 8504233 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6600. Min Act: -0.1700
Data Index: 5990644 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5974. Min Act: -0.1700
Data Index: 7374261 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6131. Min Act: -0.1700
Data Index: 7141136 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5818. Min Act: -0.1700
Data Index: 7917880 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5818. Min Act: -0.1700
Data Index: 7167978 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.6131. Min Act: -0.1700
Data Index: 7069431 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5505. Min Act: -0.1700
Data Index: 5764295 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5348. Min Act: -0.1700
Data Index: 2944138 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9102. Min Range: -3.9102
Max Act: 3.5348. Min Act: -0.1700
Data Index: 3987243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19