Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.6582. Min Act: -0.1700
Data Index: 8066790 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.2520. Min Act: -0.1700
Data Index: 7380262 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.2207. Min Act: -0.1700
Data Index: 3160761 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0957. Min Act: -0.1700
Data Index: 2314911 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0644. Min Act: -0.1700
Data Index: 6097090 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0019. Min Act: -0.1700
Data Index: 4281937 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0019. Min Act: -0.1700
Data Index: 605911 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0019. Min Act: -0.1700
Data Index: 6097106 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6582. Min Range: -4.6582
Max Act: 4.0332. Min Act: -0.1700
Data Index: 7991158 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9707. Min Act: -0.1700
Data Index: 5451041 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9707. Min Act: -0.1700
Data Index: 7354658 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9707. Min Act: -0.1700
Data Index: 6097079 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9394. Min Act: -0.1700
Data Index: 4609981 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9707. Min Act: -0.1700
Data Index: 1597608 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9394. Min Act: -0.1700
Data Index: 1650711 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9081. Min Act: -0.1700
Data Index: 4852702 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9394. Min Act: -0.1700
Data Index: 211796 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9394. Min Act: -0.1700
Data Index: 749653 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.9081. Min Act: -0.1700
Data Index: 6097099 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6582. Min Range: -4.6582
Max Act: 3.8769. Min Act: -0.1700
Data Index: 3288614 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19