Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.2588. Min Act: -0.1700
Data Index: 5923417 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.2423. Min Act: -0.1700
Data Index: 2588462 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.2588. Min Act: -0.1700
Data Index: 5133002 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.2588. Min Act: -0.1700
Data Index: 6044928 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.2091. Min Act: -0.1700
Data Index: 3367456 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1759. Min Act: -0.1700
Data Index: 8317154 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1759. Min Act: -0.1700
Data Index: 1320187 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1593. Min Act: -0.1700
Data Index: 842793 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1593. Min Act: -0.1700
Data Index: 8439051 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 3213253 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 3110515 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 5803229 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 7344014 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1593. Min Act: -0.1700
Data Index: 4034208 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1259. Min Act: -0.1700
Data Index: 812543 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 7503250 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1092. Min Act: -0.1700
Data Index: 2831637 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1259. Min Act: -0.1700
Data Index: 4113331 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 5474826 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2588. Min Range: -2.2588
Max Act: 2.1426. Min Act: -0.1700
Data Index: 4107942 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19