Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2907. Min Range: -8.2907
Max Act: 8.2907. Min Act: -0.1700
Data Index: 91057 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2907. Min Range: -8.2907
Max Act: 8.1657. Min Act: -0.1700
Data Index: 586661 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2907. Min Range: -8.2907
Max Act: 8.1032. Min Act: -0.1700
Data Index: 2361316 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.9469. Min Act: -0.1700
Data Index: 8034314 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.9469. Min Act: -0.1700
Data Index: 2361322 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.8532. Min Act: -0.1700
Data Index: 7418297 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.7282. Min Act: -0.1700
Data Index: 8343552 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.6657. Min Act: -0.1700
Data Index: 8628573 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.6344. Min Act: -0.1700
Data Index: 1079122 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.5719. Min Act: -0.1700
Data Index: 1972477 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.5407. Min Act: -0.1700
Data Index: 767680 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.4469. Min Act: -0.1700
Data Index: 336140 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.4469. Min Act: -0.1700
Data Index: 3707798 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3844. Min Act: -0.1700
Data Index: 4775467 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3844. Min Act: -0.1700
Data Index: 7598403 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3844. Min Act: -0.1700
Data Index: 2415723 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3532. Min Act: -0.1700
Data Index: 3078749 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3532. Min Act: -0.1700
Data Index: 8636402 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.3219. Min Act: -0.1700
Data Index: 5456507 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2907. Min Range: -8.2907
Max Act: 7.2907. Min Act: -0.1700
Data Index: 3180470 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19