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

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

Neuron 463 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.5315. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.2995. Min Act: -0.0001

Data Index: 1056639 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1220. Min Act: -0.0001

Data Index: 434281 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.2161. Min Act: -0.0001

Data Index: 939986 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1151755 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1522. Min Act: -0.0001

Data Index: 287184 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0866. Min Act: -0.0001

Data Index: 42319 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0123. Min Act: -0.0001

Data Index: 1308271 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1225. Min Act: -0.0001

Data Index: 536409 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1105. Min Act: -0.0001

Data Index: 56204 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1079. Min Act: -0.0001

Data Index: 768688 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1396. Min Act: -0.0001

Data Index: 1042116 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0080. Min Act: -0.0001

Data Index: 680251 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0520. Min Act: -0.0001

Data Index: 1018158 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0518. Min Act: -0.0001

Data Index: 445660 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.1597. Min Act: -0.0001

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0732. Min Act: -0.0001

Data Index: 587017 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0820. Min Act: -0.0001

Data Index: 974371 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.5315. Min Range: -1.5315

Max Act: 0.9670. Min Act: -0.0001

Data Index: 208962 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.5315. Min Range: -1.5315

Max Act: 1.0216. Min Act: -0.0001

Data Index: 1274517 (C4 (Web Text))

Max Activating Token Index: 171