Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1901 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0586. Min Range: -7.0586
Max Act: 7.0586. Min Act: -0.1700
Data Index: 6994717 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.9961. Min Act: -0.1700
Data Index: 3784436 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.9336. Min Act: -0.1700
Data Index: 8160014 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.8711. Min Act: -0.1700
Data Index: 271572 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.8711. Min Act: -0.1700
Data Index: 7571850 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.8399. Min Act: -0.1700
Data Index: 7683519 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.8399. Min Act: -0.1700
Data Index: 1009482 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7461. Min Act: -0.1700
Data Index: 3986107 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7461. Min Act: -0.1700
Data Index: 1422073 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7149. Min Act: -0.1700
Data Index: 5747478 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7149. Min Act: -0.1700
Data Index: 1333263 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7149. Min Act: -0.1700
Data Index: 1309033 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7149. Min Act: -0.1700
Data Index: 5679813 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.7461. Min Act: -0.1700
Data Index: 5414130 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6474387 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 1759750 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 3098191 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 7285889 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 3626846 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0586. Min Range: -7.0586
Max Act: 6.6836. Min Act: -0.1700
Data Index: 5234462 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19