Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1100. Min Range: -6.1100
Max Act: 6.1100. Min Act: -0.1700
Data Index: 3984475 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1100. Min Range: -6.1100
Max Act: 6.0475. Min Act: -0.1700
Data Index: 5047417 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1100. Min Range: -6.1100
Max Act: 6.0475. Min Act: -0.1700
Data Index: 7841074 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9850. Min Act: -0.1700
Data Index: 4613674 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 7502217 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 7841069 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 5444616 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2747473 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.9225. Min Act: -0.1700
Data Index: 6272841 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5047427 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5047409 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 8586931 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8912. Min Act: -0.1700
Data Index: 1458822 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 5047426 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 3483517 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 6512321 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 8320512 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8600. Min Act: -0.1700
Data Index: 2636473 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2229848 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1100. Min Range: -6.1100
Max Act: 5.8287. Min Act: -0.1700
Data Index: 6636195 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19