Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.9411. Min Act: -0.1700
Data Index: 1774866 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.8786. Min Act: -0.1700
Data Index: 1957205 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6599. Min Act: -0.1700
Data Index: 5627150 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6599. Min Act: -0.1700
Data Index: 3110814 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 4445432 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 8830419 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 4836061 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6599. Min Act: -0.1700
Data Index: 1448413 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 2297444 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 1645583 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5974. Min Act: -0.1700
Data Index: 891694 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.6286. Min Act: -0.1700
Data Index: 4109594 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5974. Min Act: -0.1700
Data Index: 8350377 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5349. Min Act: -0.1700
Data Index: 1430451 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 6112465 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 3206130 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5349. Min Act: -0.1700
Data Index: 6210539 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 2817925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 1770785 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9411. Min Range: -4.9411
Max Act: 4.5661. Min Act: -0.1700
Data Index: 6880825 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19