Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2758. Min Act: -0.0001

Data Index: 161582 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2144. Min Act: -0.0000

Data Index: 3797 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2567. Min Act: -0.0001

Data Index: 845915 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1082657 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2342. Min Act: -0.0001

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2693. Min Act: -0.0001

Data Index: 65147 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1870. Min Act: -0.0001

Data Index: 242767 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1912. Min Act: -0.0001

Data Index: 804978 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1034. Min Act: -0.0000

Data Index: 658976 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1594. Min Act: -0.0001

Data Index: 1103565 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1351. Min Act: -0.0001

Data Index: 225156 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1305. Min Act: -0.0001

Data Index: 908160 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2957. Min Act: -0.0000

Data Index: 826174 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2002. Min Act: -0.0000

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1197247 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1079. Min Act: -0.0000

Data Index: 454641 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0272. Min Act: -0.0001

Data Index: 1267229 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2149. Min Act: -0.0001

Data Index: 264676 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.3281. Min Act: -0.0000

Data Index: 282145 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1220. Min Act: -0.0001

Data Index: 513702 (C4 (Web Text))

Max Activating Token Index: 655