Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1921. Min Range: -7.1921
Max Act: 7.1921. Min Act: -0.1700
Data Index: 5672569 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.9421. Min Act: -0.1700
Data Index: 6721141 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.9421. Min Act: -0.1700
Data Index: 7070296 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.9109. Min Act: -0.1700
Data Index: 4883605 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.8484. Min Act: -0.1700
Data Index: 698096 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7859. Min Act: -0.1700
Data Index: 3635026 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7546. Min Act: -0.1700
Data Index: 2037568 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7546. Min Act: -0.1700
Data Index: 1759399 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4329720 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4196854 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6609. Min Act: -0.1700
Data Index: 445659 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6296. Min Act: -0.1700
Data Index: 5081175 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6296. Min Act: -0.1700
Data Index: 7179992 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5984. Min Act: -0.1700
Data Index: 1487900 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6296. Min Act: -0.1700
Data Index: 3134178 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 3383457 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1324265 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 5528104 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1579636 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.5046. Min Act: -0.1700
Data Index: 5109780 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19