Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2090 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9498. Min Range: -8.9498
Max Act: 8.9498. Min Act: -0.1700
Data Index: 4789331 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9498. Min Range: -8.9498
Max Act: 8.0436. Min Act: -0.1700
Data Index: 5796163 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9498. Min Range: -8.9498
Max Act: 8.0436. Min Act: -0.1700
Data Index: 227592 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9811. Min Act: -0.1700
Data Index: 1617826 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9498. Min Act: -0.1700
Data Index: 2320769 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9498. Min Act: -0.1700
Data Index: 2526596 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9498. Min Act: -0.1700
Data Index: 8332461 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9186. Min Act: -0.1700
Data Index: 3619926 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.9186. Min Act: -0.1700
Data Index: 2808531 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.8873. Min Act: -0.1700
Data Index: 6862475 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.8561. Min Act: -0.1700
Data Index: 2489993 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.8248. Min Act: -0.1700
Data Index: 2709979 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7936. Min Act: -0.1700
Data Index: 7982238 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7936. Min Act: -0.1700
Data Index: 2512393 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7936. Min Act: -0.1700
Data Index: 2996520 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7623. Min Act: -0.1700
Data Index: 348010 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7623. Min Act: -0.1700
Data Index: 3295079 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7311. Min Act: -0.1700
Data Index: 2587456 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7311. Min Act: -0.1700
Data Index: 6085899 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9498. Min Range: -8.9498
Max Act: 7.7311. Min Act: -0.1700
Data Index: 1452581 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19