Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0385. Min Act: -0.0000

Data Index: 34804 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0000

Data Index: 27368 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0377. Min Act: -0.0000

Data Index: 795509 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1323302 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0346. Min Act: -0.0000

Data Index: 205020 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0322. Min Act: -0.0000

Data Index: 807813 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0298. Min Act: -0.0000

Data Index: 720047 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0320. Min Act: -0.0000

Data Index: 608188 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0308. Min Act: -0.0000

Data Index: 1022107 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0309. Min Act: -0.0000

Data Index: 435675 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0341. Min Act: -0.0000

Data Index: 786102 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0319. Min Act: -0.0000

Data Index: 772434 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1472841 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0290. Min Act: -0.0000

Data Index: 780485 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0285. Min Act: -0.0000

Data Index: 778152 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1124428 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0282. Min Act: -0.0000

Data Index: 656122 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0293. Min Act: -0.0000

Data Index: 457090 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0281. Min Act: -0.0000

Data Index: 918421 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0278. Min Act: -0.0000

Data Index: 594027 (C4 (Web Text))

Max Activating Token Index: 924