Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1110 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.5108. Min Act: -0.1700
Data Index: 4847234 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.3546. Min Act: -0.1700
Data Index: 4088286 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.2921. Min Act: -0.1700
Data Index: 1399901 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.2921. Min Act: -0.1700
Data Index: 641883 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.1358. Min Act: -0.1700
Data Index: 5510082 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.0733. Min Act: -0.1700
Data Index: 6283948 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5108. Min Range: -7.5108
Max Act: 7.0421. Min Act: -0.1700
Data Index: 2094026 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 2256622 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 4567432 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 8809086 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 2007806 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9171. Min Act: -0.1700
Data Index: 1460797 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9171. Min Act: -0.1700
Data Index: 4180947 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9171. Min Act: -0.1700
Data Index: 1940385 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.9483. Min Act: -0.1700
Data Index: 4705087 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.8858. Min Act: -0.1700
Data Index: 591627 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.8858. Min Act: -0.1700
Data Index: 2076821 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.8546. Min Act: -0.1700
Data Index: 6157106 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.8858. Min Act: -0.1700
Data Index: 1480314 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5108. Min Range: -7.5108
Max Act: 6.8546. Min Act: -0.1700
Data Index: 5779962 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19