Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.3652. Min Act: -0.1700
Data Index: 935754 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.3027. Min Act: -0.1700
Data Index: 4420177 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.2714. Min Act: -0.1700
Data Index: 5167764 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.2402. Min Act: -0.1700
Data Index: 6047116 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.2402. Min Act: -0.1700
Data Index: 7076024 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.1777. Min Act: -0.1700
Data Index: 6082014 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0839. Min Act: -0.1700
Data Index: 2906906 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.1152. Min Act: -0.1700
Data Index: 6047114 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0527. Min Act: -0.1700
Data Index: 5918329 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0527. Min Act: -0.1700
Data Index: 5454857 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0527. Min Act: -0.1700
Data Index: 4955100 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0214. Min Act: -0.1700
Data Index: 1508296 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3652. Min Range: -6.3652
Max Act: 5.9902. Min Act: -0.1700
Data Index: 8316971 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0214. Min Act: -0.1700
Data Index: 7157270 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0214. Min Act: -0.1700
Data Index: 1144207 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2825312 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3652. Min Range: -6.3652
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5446555 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3652. Min Range: -6.3652
Max Act: 5.9902. Min Act: -0.1700
Data Index: 6544635 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3652. Min Range: -6.3652
Max Act: 5.9589. Min Act: -0.1700
Data Index: 5786187 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3652. Min Range: -6.3652
Max Act: 5.9589. Min Act: -0.1700
Data Index: 3411933 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19