Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2534. Min Range: -9.2534
Max Act: 9.2534. Min Act: -0.1700
Data Index: 4099720 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2534. Min Range: -9.2534
Max Act: 9.1284. Min Act: -0.1700
Data Index: 8588219 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2534. Min Range: -9.2534
Max Act: 9.0659. Min Act: -0.1700
Data Index: 7914673 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2534. Min Range: -9.2534
Max Act: 9.0034. Min Act: -0.1700
Data Index: 1748645 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 7421787 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.9409. Min Act: -0.1700
Data Index: 6019505 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.9409. Min Act: -0.1700
Data Index: 7027392 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 2083348 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 6121032 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 5297618 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 1418766 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8784. Min Act: -0.1700
Data Index: 4656526 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8159. Min Act: -0.1700
Data Index: 7914671 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8159. Min Act: -0.1700
Data Index: 4739036 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.8159. Min Act: -0.1700
Data Index: 7840538 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.7534. Min Act: -0.1700
Data Index: 2928880 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.6284. Min Act: -0.1700
Data Index: 4013060 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.6909. Min Act: -0.1700
Data Index: 3771338 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.6284. Min Act: -0.1700
Data Index: 3229252 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2534. Min Range: -9.2534
Max Act: 8.6284. Min Act: -0.1700
Data Index: 6532004 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19