Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 994 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6645. Min Act: -0.1700
Data Index: 5488842 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6645. Min Act: -0.1700
Data Index: 2975518 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6645. Min Act: -0.1700
Data Index: 4515765 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6324. Min Act: -0.1700
Data Index: 6907743 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6164. Min Act: -0.1700
Data Index: 4732704 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6164. Min Act: -0.1700
Data Index: 6882862 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6003. Min Act: -0.1700
Data Index: 517199 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.6324. Min Act: -0.1698
Data Index: 7996297 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5842. Min Act: -0.1700
Data Index: 2516639 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5519. Min Act: -0.1700
Data Index: 5568466 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5681. Min Act: -0.1700
Data Index: 1360868 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5681. Min Act: -0.1700
Data Index: 615883 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5681. Min Act: -0.1700
Data Index: 760529 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5358. Min Act: -0.1700
Data Index: 5366367 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5681. Min Act: -0.1700
Data Index: 3374981 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5358. Min Act: -0.1700
Data Index: 6141609 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5358. Min Act: -0.1700
Data Index: 6045861 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5519. Min Act: -0.1700
Data Index: 3313740 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5519. Min Act: -0.1700
Data Index: 2444923 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6645. Min Range: -2.6645
Max Act: 2.5358. Min Act: -0.1700
Data Index: 8037935 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19