Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 803 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.6791. Min Act: -0.1700
Data Index: 2265066 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.4291. Min Act: -0.1700
Data Index: 8072009 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.0853. Min Act: -0.1700
Data Index: 8589682 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.0853. Min Act: -0.1700
Data Index: 4912852 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6572652 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6791. Min Range: -6.6791
Max Act: 6.0228. Min Act: -0.1700
Data Index: 856949 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6986386 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9916. Min Act: -0.1700
Data Index: 2171355 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9603. Min Act: -0.1700
Data Index: 1042575 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9603. Min Act: -0.1700
Data Index: 5307076 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9603. Min Act: -0.1700
Data Index: 6859347 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.9603. Min Act: -0.1700
Data Index: 4807146 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8978. Min Act: -0.1700
Data Index: 3512557 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8978. Min Act: -0.1700
Data Index: 1148282 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8978. Min Act: -0.1700
Data Index: 8784869 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8666. Min Act: -0.1700
Data Index: 8780601 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8666. Min Act: -0.1700
Data Index: 846760 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8353. Min Act: -0.1700
Data Index: 5044377 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8041. Min Act: -0.1700
Data Index: 7074253 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6791. Min Range: -6.6791
Max Act: 5.8041. Min Act: -0.1700
Data Index: 2006309 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19