Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.6553. Min Act: -0.1700
Data Index: 8619248 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.6241. Min Act: -0.1700
Data Index: 5172506 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.6241. Min Act: -0.1700
Data Index: 4001444 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.5303. Min Act: -0.1700
Data Index: 5891276 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.5303. Min Act: -0.1700
Data Index: 2673992 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.5303. Min Act: -0.1700
Data Index: 3445619 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.4366. Min Act: -0.1700
Data Index: 2169853 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3544746 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 5121694 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 972453 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 7649744 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.4053. Min Act: -0.1700
Data Index: 2549549 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 7598630 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 3246416 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 1976516 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 760154 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3741. Min Act: -0.1700
Data Index: 162304 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3428. Min Act: -0.1700
Data Index: 548197 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3428. Min Act: -0.1700
Data Index: 1581925 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6553. Min Range: -5.6553
Max Act: 5.3428. Min Act: -0.1700
Data Index: 5750754 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19