Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3665. Min Range: -4.3665
Max Act: 4.3665. Min Act: -0.1700
Data Index: 4042853 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3665. Min Range: -4.3665
Max Act: 4.2415. Min Act: -0.1700
Data Index: 8176080 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3665. Min Range: -4.3665
Max Act: 4.0227. Min Act: -0.1700
Data Index: 3632766 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3665. Min Range: -4.3665
Max Act: 4.0539. Min Act: -0.1700
Data Index: 7264319 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.9914. Min Act: -0.1700
Data Index: 2716364 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 1553905 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 4470276 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 8733848 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 1347668 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 3164375 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8976. Min Act: -0.1700
Data Index: 5573320 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8664. Min Act: -0.1700
Data Index: 4450737 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8351. Min Act: -0.1700
Data Index: 2840979 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8351. Min Act: -0.1700
Data Index: 553524 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8038. Min Act: -0.1700
Data Index: 3970568 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.7725. Min Act: -0.1700
Data Index: 3910584 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8038. Min Act: -0.1700
Data Index: 8209691 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8038. Min Act: -0.1700
Data Index: 4193822 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.7725. Min Act: -0.1700
Data Index: 53361 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3665. Min Range: -4.3665
Max Act: 3.8038. Min Act: -0.1700
Data Index: 6915132 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19