Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.4566. Min Act: -0.1700
Data Index: 8545186 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.4409. Min Act: -0.1700
Data Index: 1690405 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.4409. Min Act: -0.1700
Data Index: 7056109 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.4566. Min Act: -0.1700
Data Index: 2896792 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.4096. Min Act: -0.1700
Data Index: 895360 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.3782. Min Act: -0.1700
Data Index: 8469407 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.3469. Min Act: -0.1700
Data Index: 6419812 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.3312. Min Act: -0.1700
Data Index: 8797871 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.3312. Min Act: -0.1700
Data Index: 6283017 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2998. Min Act: -0.1700
Data Index: 891473 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2841. Min Act: -0.1700
Data Index: 4040755 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2527. Min Act: -0.1700
Data Index: 3057413 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2055. Min Act: -0.1700
Data Index: 7575714 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2212. Min Act: -0.1700
Data Index: 1452434 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2055. Min Act: -0.1700
Data Index: 4506806 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2055. Min Act: -0.1700
Data Index: 7606236 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.1898. Min Act: -0.1700
Data Index: 3051874 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.2055. Min Act: -0.1700
Data Index: 4269777 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.1898. Min Act: -0.1700
Data Index: 7388617 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4566. Min Range: -3.4566
Max Act: 3.1898. Min Act: -0.1700
Data Index: 1642261 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19