Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3799. Min Act: -0.1700
Data Index: 2761777 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3487. Min Act: -0.1700
Data Index: 8687527 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.3487. Min Act: -0.1700
Data Index: 8772001 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2862. Min Act: -0.1700
Data Index: 4059806 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2549. Min Act: -0.1700
Data Index: 7283443 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2549. Min Act: -0.1700
Data Index: 743987 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2237. Min Act: -0.1700
Data Index: 2475031 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2237. Min Act: -0.1700
Data Index: 3627674 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2237. Min Act: -0.1700
Data Index: 3435630 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.2237. Min Act: -0.1700
Data Index: 3100565 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1924. Min Act: -0.1700
Data Index: 19873 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1924. Min Act: -0.1699
Data Index: 7639886 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1924. Min Act: -0.1700
Data Index: 5738004 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1924. Min Act: -0.1700
Data Index: 4473114 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 3105816 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 573047 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 3108800 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 2893441 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 3125927 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3799. Min Range: -4.3799
Max Act: 4.1612. Min Act: -0.1700
Data Index: 19872 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19