Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.2493. Min Act: -0.1700
Data Index: 5015187 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.1868. Min Act: -0.1700
Data Index: 860086 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.1556. Min Act: -0.1700
Data Index: 879057 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.1243. Min Act: -0.1700
Data Index: 5861389 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0618. Min Act: -0.1700
Data Index: 4841028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 6070766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 455543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 2618569 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 859087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1915729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 728450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1898097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 2264865 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 880767 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 2114915 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 330257 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 508285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1320927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1872680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2493. Min Range: -5.2493
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1572399 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19