Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.2256. Min Act: -0.1700
Data Index: 5810190 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.2256. Min Act: -0.1700
Data Index: 2954660 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.2256. Min Act: -0.1700
Data Index: 7183256 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1631. Min Act: -0.1700
Data Index: 4547312 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1319. Min Act: -0.1700
Data Index: 5785703 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1631. Min Act: -0.1700
Data Index: 1974941 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1006. Min Act: -0.1700
Data Index: 6335421 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1006. Min Act: -0.1700
Data Index: 5517128 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1006. Min Act: -0.1700
Data Index: 2697142 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0694. Min Act: -0.1700
Data Index: 2129694 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1006. Min Act: -0.1700
Data Index: 1999607 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0694. Min Act: -0.1700
Data Index: 6543644 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0694. Min Act: -0.1700
Data Index: 3565551 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0068. Min Act: -0.1700
Data Index: 7297502 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0068. Min Act: -0.1700
Data Index: 5165892 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9756. Min Act: -0.1700
Data Index: 384237 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9756. Min Act: -0.1700
Data Index: 5099444 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9756. Min Act: -0.1700
Data Index: 2494904 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9756. Min Act: -0.1700
Data Index: 4140369 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9756. Min Act: -0.1700
Data Index: 5563983 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19