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

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

Neuron 3580 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: 2.9085. Min Range: -2.9085

Max Act: 2.9085. Min Act: -0.0000

Data Index: 255433 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.4457. Min Act: -0.0000

Data Index: 1565474 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.3966. Min Act: -0.0000

Data Index: 572472 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.3711. Min Act: -0.0000

Data Index: 1420525 (Python Code)

Max Activating Token Index: 509

Text #4

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2047. Min Act: -0.0000

Data Index: 708510 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.3128. Min Act: -0.0000

Data Index: 458294 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1385131 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2339. Min Act: -0.0000

Data Index: 1609138 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2161. Min Act: -0.0000

Data Index: 529206 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.3210. Min Act: -0.0000

Data Index: 135701 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1251171 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2130. Min Act: -0.0000

Data Index: 1567424 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.1808. Min Act: -0.0000

Data Index: 1480161 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2682. Min Act: -0.0000

Data Index: 973179 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.1474. Min Act: -0.0000

Data Index: 468746 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2426. Min Act: -0.0000

Data Index: 1524260 (Python Code)

Max Activating Token Index: 637

Text #16

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2153. Min Act: -0.0000

Data Index: 1393197 (Python Code)

Max Activating Token Index: 601

Text #17

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.2172. Min Act: -0.0000

Data Index: 1030974 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 2.9085. Min Range: -2.9085

Max Act: 1.9654. Min Act: -0.0000

Data Index: 1624612 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 2.9085. Min Range: -2.9085

Max Act: 2.0770. Min Act: -0.0000

Data Index: 1493897 (Python Code)

Max Activating Token Index: 760