Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0468. Min Range: -5.0468
Max Act: 5.0468. Min Act: -0.1700
Data Index: 3619003 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0468. Min Range: -5.0468
Max Act: 5.0156. Min Act: -0.1700
Data Index: 7281626 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.9843. Min Act: -0.1700
Data Index: 6059702 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.9531. Min Act: -0.1700
Data Index: 393385 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.8593. Min Act: -0.1700
Data Index: 7988491 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.8281. Min Act: -0.1700
Data Index: 8068906 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.7343. Min Act: -0.1700
Data Index: 6831042 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.7343. Min Act: -0.1700
Data Index: 8659075 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.7343. Min Act: -0.1700
Data Index: 2688825 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.7031. Min Act: -0.1700
Data Index: 3424703 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6718. Min Act: -0.1700
Data Index: 2329930 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6718. Min Act: -0.1700
Data Index: 6654450 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6718. Min Act: -0.1700
Data Index: 3657470 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6718. Min Act: -0.1700
Data Index: 1995271 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6718. Min Act: -0.1700
Data Index: 789897 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6093. Min Act: -0.1700
Data Index: 5174425 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6406. Min Act: -0.1700
Data Index: 815544 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6093. Min Act: -0.1700
Data Index: 1484382 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6406. Min Act: -0.1700
Data Index: 386230 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0468. Min Range: -5.0468
Max Act: 4.6093. Min Act: -0.1700
Data Index: 3802451 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19