Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3911626 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.2646. Min Act: -0.1700
Data Index: 6076430 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.1709. Min Act: -0.1700
Data Index: 3190655 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.1396. Min Act: -0.1700
Data Index: 8274290 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.1396. Min Act: -0.1700
Data Index: 3122839 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.0771. Min Act: -0.1700
Data Index: 6262720 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.0459. Min Act: -0.1700
Data Index: 91756 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2959. Min Range: -6.2959
Max Act: 6.0146. Min Act: -0.1700
Data Index: 7021620 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.9834. Min Act: -0.1700
Data Index: 7247983 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.9834. Min Act: -0.1700
Data Index: 5979964 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.9209. Min Act: -0.1700
Data Index: 2898781 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.9209. Min Act: -0.1700
Data Index: 1532786 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8584. Min Act: -0.1700
Data Index: 1061186 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8271. Min Act: -0.1700
Data Index: 5191701 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8584. Min Act: -0.1700
Data Index: 776009 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8584. Min Act: -0.1700
Data Index: 4348249 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8584. Min Act: -0.1700
Data Index: 1996196 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8271. Min Act: -0.1700
Data Index: 5140972 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8584. Min Act: -0.1700
Data Index: 465000 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2959. Min Range: -6.2959
Max Act: 5.8271. Min Act: -0.1700
Data Index: 650143 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19