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

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

Neuron 448 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1131039 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4770. Min Act: -0.0000

Data Index: 569147 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1043446 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.1267. Min Act: -0.0000

Data Index: 900118 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.0275. Min Act: -0.0000

Data Index: 155263 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1084589 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.0210. Min Act: -0.0000

Data Index: 142828 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9338. Min Act: -0.0000

Data Index: 292439 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9640. Min Act: -0.0000

Data Index: 242811 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9997. Min Act: -0.0000

Data Index: 981355 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1001130 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9626. Min Act: -0.0000

Data Index: 593842 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8228. Min Act: -0.0000

Data Index: 725440 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1202129 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9131. Min Act: -0.0000

Data Index: 608262 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8888. Min Act: -0.0000

Data Index: 929751 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8323. Min Act: 0.0000

Data Index: 533544 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1076713 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1066383 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1298858 (C4 (Web Text))

Max Activating Token Index: 512