Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0764. Min Range: -4.0764
Max Act: 4.0764. Min Act: -0.1688
Data Index: 4204858 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0764. Min Range: -4.0764
Max Act: 4.0452. Min Act: -0.1699
Data Index: 747898 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0764. Min Range: -4.0764
Max Act: 4.0139. Min Act: -0.1700
Data Index: 3011319 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.8263. Min Act: -0.1700
Data Index: 1432745 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.8263. Min Act: -0.1700
Data Index: 7457542 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7638. Min Act: -0.1700
Data Index: 2230046 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7638. Min Act: -0.1700
Data Index: 8530593 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7325. Min Act: -0.1700
Data Index: 5114328 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7325. Min Act: -0.1700
Data Index: 2371485 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7638. Min Act: -0.1700
Data Index: 8470926 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.7012. Min Act: -0.1700
Data Index: 961572 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6386. Min Act: -0.1693
Data Index: 1000840 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6699. Min Act: -0.1700
Data Index: 8813340 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6386. Min Act: -0.1700
Data Index: 5474650 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6386. Min Act: -0.1700
Data Index: 5624026 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6386. Min Act: -0.1700
Data Index: 6559179 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6386. Min Act: -0.1700
Data Index: 932590 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6073. Min Act: -0.1700
Data Index: 6647686 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.6073. Min Act: -0.1700
Data Index: 6970418 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0764. Min Range: -4.0764
Max Act: 3.5760. Min Act: -0.1700
Data Index: 8445623 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19