Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.9856. Min Act: -0.1700
Data Index: 5721492 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.9231. Min Act: -0.1700
Data Index: 427736 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.7981. Min Act: -0.1700
Data Index: 7106717 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.8293. Min Act: -0.1700
Data Index: 6630003 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.7356. Min Act: -0.1700
Data Index: 4620596 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.6731. Min Act: -0.1700
Data Index: 5334668 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.6106. Min Act: -0.1700
Data Index: 6824528 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5793. Min Act: -0.1700
Data Index: 6245975 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8763230 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 2830610 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 3182269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 2841084 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 958984 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 2969659 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3452393 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 6318076 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3729517 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1432955 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.5168. Min Act: -0.1700
Data Index: 1730594 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9856. Min Range: -6.9856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 7327153 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19