Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.7477. Min Act: -0.1700
Data Index: 4289808 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6539. Min Act: -0.1700
Data Index: 6167365 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6539. Min Act: -0.1700
Data Index: 216740 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7863851 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6539. Min Act: -0.1700
Data Index: 1809311 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7232004 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6227. Min Act: -0.1700
Data Index: 4607937 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6227. Min Act: -0.1700
Data Index: 2258522 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.6227. Min Act: -0.1700
Data Index: 7607644 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5914. Min Act: -0.1700
Data Index: 1830078 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 5577095 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5914. Min Act: -0.1700
Data Index: 849308 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5914. Min Act: -0.1700
Data Index: 1684189 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5914. Min Act: -0.1700
Data Index: 6312996 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 157617 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 2527397 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 2845492 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 5103410 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6667219 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7477. Min Range: -6.7477
Max Act: 6.5602. Min Act: -0.1700
Data Index: 3696662 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19