Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.9879. Min Act: -0.1700
Data Index: 2330267 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.9566. Min Act: -0.1700
Data Index: 5922805 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.8941. Min Act: -0.1700
Data Index: 5280279 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.8629. Min Act: -0.1700
Data Index: 3134135 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.8004. Min Act: -0.1700
Data Index: 3843581 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.8004. Min Act: -0.1700
Data Index: 4692926 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7691. Min Act: -0.1700
Data Index: 5341499 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7379. Min Act: -0.1700
Data Index: 7418269 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8120025 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8431620 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 7175962 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7379. Min Act: -0.1700
Data Index: 414080 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7066. Min Act: -0.1700
Data Index: 3975557 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.7066. Min Act: -0.1700
Data Index: 4848811 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 4419005 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 2378427 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 38725 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 3835814 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6754. Min Act: -0.1700
Data Index: 1748 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9879. Min Range: -4.9879
Max Act: 4.6441. Min Act: -0.1700
Data Index: 5071454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19