Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.2018. Min Act: -0.1700
Data Index: 6629849 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1841. Min Act: -0.1700
Data Index: 7331482 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1754. Min Act: -0.1700
Data Index: 1777294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1578. Min Act: -0.1700
Data Index: 8077233 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1402. Min Act: -0.1700
Data Index: 5025406 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1402. Min Act: -0.1700
Data Index: 408392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1314. Min Act: -0.1700
Data Index: 4739263 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1139. Min Act: -0.1700
Data Index: 3514471 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1051. Min Act: -0.1700
Data Index: 8147640 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1139. Min Act: -0.1700
Data Index: 1973792 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1139. Min Act: -0.1700
Data Index: 4712294 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1051. Min Act: -0.1700
Data Index: 5033331 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1051. Min Act: -0.1700
Data Index: 3178907 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.1051. Min Act: -0.1700
Data Index: 2726184 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0963. Min Act: -0.1700
Data Index: 5749732 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0876. Min Act: -0.1700
Data Index: 6502154 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0876. Min Act: -0.1700
Data Index: 1023118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0876. Min Act: -0.1700
Data Index: 3591082 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0876. Min Act: -0.1700
Data Index: 728850 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2018. Min Range: -1.2018
Max Act: 1.0876. Min Act: -0.1700
Data Index: 2711005 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19