Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.5751. Min Act: -0.1700
Data Index: 5933642 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.5439. Min Act: -0.1700
Data Index: 7399845 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.2939. Min Act: -0.1700
Data Index: 599367 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.2939. Min Act: -0.1700
Data Index: 7077041 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.2939. Min Act: -0.1700
Data Index: 1452199 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.0439. Min Act: -0.1700
Data Index: 7024272 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.0751. Min Act: -0.1700
Data Index: 7644499 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.0439. Min Act: -0.1700
Data Index: 6381417 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5751. Min Range: -7.5751
Max Act: 7.0126. Min Act: -0.1700
Data Index: 1322187 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9814. Min Act: -0.1700
Data Index: 6614813 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9501. Min Act: -0.1700
Data Index: 2011193 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9501. Min Act: -0.1700
Data Index: 4668263 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9501. Min Act: -0.1700
Data Index: 6345879 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.8876. Min Act: -0.1700
Data Index: 3842155 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.8876. Min Act: -0.1700
Data Index: 5007167 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9189. Min Act: -0.1700
Data Index: 2912197 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9189. Min Act: -0.1700
Data Index: 1873525 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.9189. Min Act: -0.1700
Data Index: 904624 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.8876. Min Act: -0.1700
Data Index: 2301295 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5751. Min Range: -7.5751
Max Act: 6.8564. Min Act: -0.1700
Data Index: 600337 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19