Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6078 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.7153. Min Act: -0.1700
Data Index: 4739916 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.5903. Min Act: -0.1700
Data Index: 5830033 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.5278. Min Act: -0.1700
Data Index: 4506699 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.4028. Min Act: -0.1700
Data Index: 5437123 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.3403. Min Act: -0.1700
Data Index: 5236907 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.3090. Min Act: -0.1700
Data Index: 4445800 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.2153. Min Act: -0.1700
Data Index: 3494306 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.2153. Min Act: -0.1700
Data Index: 2803554 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.2153. Min Act: -0.1700
Data Index: 2803551 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1278968 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1278967 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.1528. Min Act: -0.1700
Data Index: 1353711 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1749101 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.1528. Min Act: -0.1700
Data Index: 2434958 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0590. Min Act: -0.1700
Data Index: 6807698 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0903. Min Act: -0.1700
Data Index: 4952815 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0903. Min Act: -0.1700
Data Index: 2195179 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0590. Min Act: -0.1700
Data Index: 8187806 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0903. Min Act: -0.1700
Data Index: 5589334 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7153. Min Range: -5.7153
Max Act: 5.0278. Min Act: -0.1700
Data Index: 5496924 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19