Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2067818 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.6296. Min Act: -0.1700
Data Index: 4424145 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5984. Min Act: -0.1700
Data Index: 7274951 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.6296. Min Act: -0.1700
Data Index: 7800881 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5671. Min Act: -0.1700
Data Index: 6091731 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5359. Min Act: -0.1700
Data Index: 2783008 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1020230 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5359. Min Act: -0.1700
Data Index: 6563155 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5359. Min Act: -0.1700
Data Index: 2153827 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5046. Min Act: -0.1700
Data Index: 386238 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.5046. Min Act: -0.1700
Data Index: 2696047 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.4734. Min Act: -0.1700
Data Index: 2113798 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.4421. Min Act: -0.1700
Data Index: 8650701 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.4421. Min Act: -0.1700
Data Index: 673570 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.4109. Min Act: -0.1700
Data Index: 6064054 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.3796. Min Act: -0.1700
Data Index: 3574435 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.3796. Min Act: -0.1700
Data Index: 2150907 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.4109. Min Act: -0.1700
Data Index: 652609 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.3484. Min Act: -0.1700
Data Index: 530273 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7234. Min Range: -6.7234
Max Act: 6.3484. Min Act: -0.1700
Data Index: 5056782 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19