Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.8047. Min Act: -0.1700
Data Index: 2367362 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.8360. Min Act: -0.1700
Data Index: 6013623 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.7421. Min Act: -0.1700
Data Index: 7199168 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.7108. Min Act: -0.1700
Data Index: 251900 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.7108. Min Act: -0.1700
Data Index: 4420624 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.6483. Min Act: -0.1700
Data Index: 6494489 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5857. Min Act: -0.1700
Data Index: 8461688 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5544. Min Act: -0.1700
Data Index: 6346475 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5857. Min Act: -0.1700
Data Index: 4611769 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5230. Min Act: -0.1700
Data Index: 8081463 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5230. Min Act: -0.1700
Data Index: 151974 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.5074. Min Act: -0.1700
Data Index: 7120815 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4917. Min Act: -0.1700
Data Index: 3293584 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4761. Min Act: -0.1700
Data Index: 5182810 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4447. Min Act: -0.1700
Data Index: 3814440 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4290. Min Act: -0.1700
Data Index: 2965192 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4290. Min Act: -0.1700
Data Index: 7960027 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4290. Min Act: -0.1700
Data Index: 7407735 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.4290. Min Act: -0.1700
Data Index: 2115484 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8360. Min Range: -3.8360
Max Act: 3.3977. Min Act: -0.1700
Data Index: 2740141 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19