Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 500 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3869. Min Act: -0.1700
Data Index: 1738446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3556. Min Act: -0.1700
Data Index: 3316500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3556. Min Act: -0.1700
Data Index: 4008098 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3556. Min Act: -0.1700
Data Index: 6329681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3556. Min Act: -0.1700
Data Index: 5639862 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3556. Min Act: -0.1700
Data Index: 34059 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4792811 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 6316467 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 6278547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 361376 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 3158502 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 1304451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4008094 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.2928. Min Act: -0.1700
Data Index: 4689212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4650045 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4008096 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 2832893 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 2167011 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4008101 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3869. Min Range: -3.3869
Max Act: 3.3242. Min Act: -0.1700
Data Index: 1642143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19