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

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

Neuron 3605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0003

Data Index: 483357 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1414858 (Python Code)

Max Activating Token Index: 521

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0363. Min Act: -0.0002

Data Index: 359625 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1394071 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0390. Min Act: -0.0002

Data Index: 171322 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1194608 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1178313 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1415056 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1615238 (Python Code)

Max Activating Token Index: 492

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1422831 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0325. Min Act: -0.0003

Data Index: 490876 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0340. Min Act: -0.0002

Data Index: 629043 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1195763 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0302. Min Act: -0.0002

Data Index: 204223 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0375. Min Act: -0.0002

Data Index: 292832 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0309. Min Act: -0.0002

Data Index: 327091 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0299. Min Act: -0.0002

Data Index: 364532 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1424722 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0280. Min Act: -0.0003

Data Index: 111938 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0289. Min Act: -0.0002

Data Index: 416146 (C4 (Web Text))

Max Activating Token Index: 706