Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.5679. Min Act: -0.1700
Data Index: 3140429 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.5523. Min Act: -0.1700
Data Index: 4673235 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.5210. Min Act: -0.1700
Data Index: 607957 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.5210. Min Act: -0.1700
Data Index: 4896323 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4896. Min Act: -0.1700
Data Index: 3143612 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4270. Min Act: -0.1700
Data Index: 7581951 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4270. Min Act: -0.1700
Data Index: 4388006 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4270. Min Act: -0.1700
Data Index: 3561344 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4426. Min Act: -0.1700
Data Index: 8445681 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.4270. Min Act: -0.1700
Data Index: 4962793 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3956. Min Act: -0.1700
Data Index: 1933296 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3956. Min Act: -0.1700
Data Index: 8602314 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3956. Min Act: -0.1700
Data Index: 921557 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3799. Min Act: -0.1700
Data Index: 1796767 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3486. Min Act: -0.1700
Data Index: 3110114 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3486. Min Act: -0.1700
Data Index: 5181699 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3486. Min Act: -0.1700
Data Index: 6346850 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3172. Min Act: -0.1700
Data Index: 6981384 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3486. Min Act: -0.1700
Data Index: 7043691 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5679. Min Range: -3.5679
Max Act: 3.3486. Min Act: -0.1700
Data Index: 3600137 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19