Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.6676. Min Act: -0.1682
Data Index: 4176906 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.6676. Min Act: -0.1700
Data Index: 2006348 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.6117. Min Act: -0.1695
Data Index: 2020011 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.6038. Min Act: -0.1700
Data Index: 8614750 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5959. Min Act: -0.1699
Data Index: 1270189 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5959. Min Act: -0.1697
Data Index: 6658288 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5725. Min Act: -0.1693
Data Index: 7105545 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5725. Min Act: -0.1692
Data Index: 2997544 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5725. Min Act: -0.1699
Data Index: 7328524 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5725. Min Act: -0.1700
Data Index: 6877548 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5647. Min Act: -0.1695
Data Index: 3878377 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5570. Min Act: -0.1699
Data Index: 7963188 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5647. Min Act: -0.1700
Data Index: 3803810 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5570. Min Act: -0.1682
Data Index: 3296459 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5339. Min Act: -0.1699
Data Index: 3428800 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5416. Min Act: -0.1699
Data Index: 2082487 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5416. Min Act: -0.1689
Data Index: 3503226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5416. Min Act: -0.1700
Data Index: 2428524 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5263. Min Act: -0.1682
Data Index: 2542006 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6676. Min Range: -0.6676
Max Act: 0.5263. Min Act: -0.1700
Data Index: 8498443 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19