Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2871. Min Range: -5.2871
Max Act: 5.2871. Min Act: -0.1700
Data Index: 1345945 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2871. Min Range: -5.2871
Max Act: 5.0996. Min Act: -0.1700
Data Index: 5530493 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2871. Min Range: -5.2871
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5530492 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2871. Min Range: -5.2871
Max Act: 5.0058. Min Act: -0.1700
Data Index: 8427439 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9746. Min Act: -0.1700
Data Index: 8133008 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9433. Min Act: -0.1700
Data Index: 6627924 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9433. Min Act: -0.1700
Data Index: 3309641 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9121. Min Act: -0.1700
Data Index: 5278330 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6540890 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9746. Min Act: -0.1700
Data Index: 3291703 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9433. Min Act: -0.1700
Data Index: 494582 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9433. Min Act: -0.1700
Data Index: 824612 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9121. Min Act: -0.1700
Data Index: 4241974 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.9121. Min Act: -0.1700
Data Index: 2644374 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7851018 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8808. Min Act: -0.1700
Data Index: 8524416 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8496. Min Act: -0.1700
Data Index: 4282931 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8496. Min Act: -0.1700
Data Index: 1929705 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8496. Min Act: -0.1700
Data Index: 3412937 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2871. Min Range: -5.2871
Max Act: 4.8496. Min Act: -0.1700
Data Index: 201579 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19