Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0346. Min Range: -8.0346
Max Act: 8.0346. Min Act: -0.1700
Data Index: 2229211 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.6596. Min Act: -0.1700
Data Index: 5507231 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5971. Min Act: -0.1700
Data Index: 1169443 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5971. Min Act: -0.1700
Data Index: 1768755 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 5756336 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 5537900 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 81596 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 2112739 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 1978020 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.5346. Min Act: -0.1700
Data Index: 1851487 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4721. Min Act: -0.1700
Data Index: 7718223 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4721. Min Act: -0.1700
Data Index: 4789439 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4409. Min Act: -0.1700
Data Index: 1716473 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4409. Min Act: -0.1700
Data Index: 1497477 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4409. Min Act: -0.1700
Data Index: 794035 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4409. Min Act: -0.1700
Data Index: 1520409 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4096. Min Act: -0.1700
Data Index: 1821786 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.4409. Min Act: -0.1700
Data Index: 4895176 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.3784. Min Act: -0.1700
Data Index: 1219250 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0346. Min Range: -8.0346
Max Act: 7.3784. Min Act: -0.1700
Data Index: 8486292 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19