Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0084. Min Range: -8.0084
Max Act: 8.0084. Min Act: -0.1700
Data Index: 5571276 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0084. Min Range: -8.0084
Max Act: 8.0084. Min Act: -0.1700
Data Index: 5208059 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.9459. Min Act: -0.1700
Data Index: 1942017 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.8834. Min Act: -0.1700
Data Index: 1527705 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.8522. Min Act: -0.1700
Data Index: 6666625 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.8209. Min Act: -0.1700
Data Index: 4758764 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.8209. Min Act: -0.1700
Data Index: 7272873 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.7897. Min Act: -0.1700
Data Index: 5908368 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.7897. Min Act: -0.1700
Data Index: 2677341 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.7272. Min Act: -0.1700
Data Index: 88469 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.6959. Min Act: -0.1700
Data Index: 8828033 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.7272. Min Act: -0.1700
Data Index: 8361088 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.6647. Min Act: -0.1700
Data Index: 3441974 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.6022. Min Act: -0.1700
Data Index: 7699403 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.6022. Min Act: -0.1700
Data Index: 6759240 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.5709. Min Act: -0.1700
Data Index: 5514201 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.5397. Min Act: -0.1700
Data Index: 3807289 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.5709. Min Act: -0.1700
Data Index: 1505862 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.5397. Min Act: -0.1700
Data Index: 1977183 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0084. Min Range: -8.0084
Max Act: 7.5397. Min Act: -0.1700
Data Index: 3139517 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19