Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.4051. Min Act: -0.1700
Data Index: 1760663 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.3426. Min Act: -0.1700
Data Index: 8343324 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.4051. Min Act: -0.1700
Data Index: 8182789 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.4051. Min Act: -0.1700
Data Index: 277433 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.3426. Min Act: -0.1700
Data Index: 8795987 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.3426. Min Act: -0.1700
Data Index: 8301572 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 8569901 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 5003594 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.3426. Min Act: -0.1700
Data Index: 7830661 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 4537786 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 7318037 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 3110277 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2801. Min Act: -0.1700
Data Index: 7062441 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.3426. Min Act: -0.1700
Data Index: 5457303 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2176. Min Act: -0.1700
Data Index: 5354760 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4051. Min Range: -11.4051
Max Act: 11.2176. Min Act: -0.1700
Data Index: 4165378 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4051. Min Range: -11.4051
Max Act: 10.8426. Min Act: -0.1700
Data Index: 4569804 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4051. Min Range: -11.4051
Max Act: 10.8426. Min Act: -0.1700
Data Index: 3348465 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4051. Min Range: -11.4051
Max Act: 10.7176. Min Act: -0.1700
Data Index: 3164702 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4051. Min Range: -11.4051
Max Act: 10.7176. Min Act: -0.1700
Data Index: 7649335 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19