Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0005

Data Index: 249875 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0375. Min Act: -0.0005

Data Index: 1062486 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0374. Min Act: -0.0005

Data Index: 398453 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1327105 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0346. Min Act: -0.0005

Data Index: 689317 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0336. Min Act: -0.0005

Data Index: 455094 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0308. Min Act: -0.0005

Data Index: 300367 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0349. Min Act: -0.0005

Data Index: 955326 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0299. Min Act: -0.0005

Data Index: 677692 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0320. Min Act: -0.0005

Data Index: 1232343 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0309. Min Act: -0.0005

Data Index: 1225984 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0308. Min Act: -0.0005

Data Index: 4505 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0295. Min Act: -0.0005

Data Index: 502623 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1258329 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0309. Min Act: -0.0005

Data Index: 93494 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0303. Min Act: -0.0005

Data Index: 1142157 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0296. Min Act: -0.0005

Data Index: 591191 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0299. Min Act: -0.0005

Data Index: 1040656 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0289. Min Act: -0.0005

Data Index: 11530 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0283. Min Act: -0.0005

Data Index: 283273 (C4 (Web Text))

Max Activating Token Index: 737