Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5540 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.9204. Min Act: -0.1700
Data Index: 1114990 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.9204. Min Act: -0.1700
Data Index: 910927 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.8266. Min Act: -0.1700
Data Index: 6245491 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.8266. Min Act: -0.1700
Data Index: 3314670 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.7954. Min Act: -0.1700
Data Index: 2367282 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6704. Min Act: -0.1700
Data Index: 7113022 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6704. Min Act: -0.1700
Data Index: 8664437 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6391. Min Act: -0.1700
Data Index: 3416212 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6391. Min Act: -0.1700
Data Index: 6524613 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6391. Min Act: -0.1700
Data Index: 8640055 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6391. Min Act: -0.1700
Data Index: 1835905 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6391. Min Act: -0.1700
Data Index: 6117884 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.6079. Min Act: -0.1700
Data Index: 8186589 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.5766. Min Act: -0.1700
Data Index: 1391407 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.5453. Min Act: -0.1700
Data Index: 467260 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.5766. Min Act: -0.1700
Data Index: 3614913 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.5141. Min Act: -0.1700
Data Index: 3116136 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.5141. Min Act: -0.1700
Data Index: 1998077 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.4828. Min Act: -0.1700
Data Index: 417455 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9204. Min Range: -4.9204
Max Act: 4.4828. Min Act: -0.1700
Data Index: 1475505 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19