Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.8976. Min Act: -0.1653
Data Index: 169698 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.6476. Min Act: -0.1697
Data Index: 6227689 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.6476. Min Act: -0.1700
Data Index: 4455881 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.5851. Min Act: -0.1700
Data Index: 3747696 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.5226. Min Act: -0.1606
Data Index: 8550056 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.5226. Min Act: -0.1700
Data Index: 2944639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.5226. Min Act: -0.1458
Data Index: 731002 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.5226. Min Act: -0.1683
Data Index: 3228578 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.4601. Min Act: -0.1649
Data Index: 1897234 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.4601. Min Act: -0.1658
Data Index: 2732268 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.4601. Min Act: -0.1699
Data Index: 8623425 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.4601. Min Act: -0.1696
Data Index: 8628331 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1508
Data Index: 8323420 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1653
Data Index: 1197176 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3351. Min Act: -0.1700
Data Index: 8271963 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1695
Data Index: 1432710 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1695
Data Index: 4992272 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1539
Data Index: 5293987 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1699
Data Index: 1738826 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8976. Min Range: -11.8976
Max Act: 11.3976. Min Act: -0.1672
Data Index: 7517386 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19