Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.6189. Min Act: -0.1700
Data Index: 5478524 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5564. Min Act: -0.1700
Data Index: 3104603 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5877. Min Act: -0.1700
Data Index: 2294881 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3276445 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5270619 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5564. Min Act: -0.1700
Data Index: 6251832 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5564. Min Act: -0.1700
Data Index: 2195700 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.5252. Min Act: -0.1700
Data Index: 1998287 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4627. Min Act: -0.1700
Data Index: 3093652 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4627. Min Act: -0.1700
Data Index: 419262 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4627. Min Act: -0.1700
Data Index: 7693322 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4627. Min Act: -0.1700
Data Index: 4136106 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4314. Min Act: -0.1700
Data Index: 5425845 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4314. Min Act: -0.1700
Data Index: 1171975 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4002. Min Act: -0.1700
Data Index: 591647 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2992790 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4002. Min Act: -0.1700
Data Index: 3969319 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4002. Min Act: -0.1700
Data Index: 557115 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.3689. Min Act: -0.1700
Data Index: 67580 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6189. Min Range: -5.6189
Max Act: 5.4002. Min Act: -0.1700
Data Index: 4727556 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19