Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.7177. Min Act: -0.0000

Data Index: 314387 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.5246. Min Act: -0.0000

Data Index: 1246509 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.5032. Min Act: -0.0000

Data Index: 1063743 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.4726. Min Act: -0.0000

Data Index: 734618 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3971. Min Act: -0.0000

Data Index: 352729 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3306. Min Act: -0.0000

Data Index: 842102 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3188. Min Act: -0.0000

Data Index: 828463 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.4124. Min Act: -0.0000

Data Index: 379171 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.2723. Min Act: -0.0000

Data Index: 738536 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3699. Min Act: -0.0000

Data Index: 66365 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1239841 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3532. Min Act: -0.0000

Data Index: 364277 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.2363. Min Act: -0.0000

Data Index: 407799 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.0047. Min Act: -0.0000

Data Index: 939412 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.3085. Min Act: -0.0000

Data Index: 757645 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.1990. Min Act: -0.0000

Data Index: 1037530 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 2.7177. Min Range: -2.7177

Max Act: 1.9424. Min Act: -0.0000

Data Index: 1302257 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.1684. Min Act: -0.0000

Data Index: 734679 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.1773. Min Act: -0.0000

Data Index: 301890 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 2.7177. Min Range: -2.7177

Max Act: 2.0348. Min Act: -0.0000

Data Index: 1019323 (C4 (Web Text))

Max Activating Token Index: 42