Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5599 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0139. Min Range: -5.0139
Max Act: 5.0139. Min Act: -0.1700
Data Index: 1855992 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.9202. Min Act: -0.1700
Data Index: 7153886 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.8577. Min Act: -0.1700
Data Index: 8506998 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.8577. Min Act: -0.1700
Data Index: 2569805 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7952. Min Act: -0.1700
Data Index: 7494278 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7952. Min Act: -0.1700
Data Index: 5410030 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7639. Min Act: -0.1700
Data Index: 6573428 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7639. Min Act: -0.1700
Data Index: 8661808 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7639. Min Act: -0.1700
Data Index: 690399 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7327. Min Act: -0.1700
Data Index: 5395466 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1179661 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1629378 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7327. Min Act: -0.1700
Data Index: 892634 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.7014. Min Act: -0.1700
Data Index: 505930 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6702. Min Act: -0.1700
Data Index: 3043498 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6702. Min Act: -0.1700
Data Index: 373797 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6389. Min Act: -0.1700
Data Index: 3561683 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6077. Min Act: -0.1700
Data Index: 4396674 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6389. Min Act: -0.1700
Data Index: 1905668 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0139. Min Range: -5.0139
Max Act: 4.6389. Min Act: -0.1700
Data Index: 4794847 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19