Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.8031. Min Act: -0.1700
Data Index: 5055571 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.7719. Min Act: -0.1700
Data Index: 2414935 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1548590 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.6781. Min Act: -0.1700
Data Index: 6652815 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.6781. Min Act: -0.1700
Data Index: 258803 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.6469. Min Act: -0.1700
Data Index: 831611 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.6469. Min Act: -0.1700
Data Index: 8792890 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.6156. Min Act: -0.1700
Data Index: 5364494 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5844. Min Act: -0.1700
Data Index: 7902290 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5531. Min Act: -0.1700
Data Index: 2587732 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5531. Min Act: -0.1700
Data Index: 6747162 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2585008 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5219. Min Act: -0.1700
Data Index: 353326 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.5219. Min Act: -0.1700
Data Index: 8805465 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4906. Min Act: -0.1700
Data Index: 2273973 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4594. Min Act: -0.1700
Data Index: 8320851 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4594. Min Act: -0.1700
Data Index: 308970 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4594. Min Act: -0.1700
Data Index: 2657773 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4594. Min Act: -0.1700
Data Index: 3022577 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8031. Min Range: -5.8031
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4297256 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19