Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 76 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0003

Data Index: 569991 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0369. Min Act: -0.0003

Data Index: 382635 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1281560 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0350. Min Act: -0.0003

Data Index: 364540 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1303114 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0347. Min Act: -0.0003

Data Index: 822036 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0348. Min Act: -0.0003

Data Index: 238765 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0336. Min Act: -0.0003

Data Index: 828536 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0336. Min Act: -0.0003

Data Index: 775782 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0333. Min Act: -0.0003

Data Index: 954637 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0340. Min Act: -0.0003

Data Index: 659364 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1342680 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0331. Min Act: -0.0003

Data Index: 125236 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0322. Min Act: -0.0003

Data Index: 727584 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1285186 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0326. Min Act: -0.0003

Data Index: 350434 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0323. Min Act: -0.0003

Data Index: 361335 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0325. Min Act: -0.0002

Data Index: 958804 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0319. Min Act: -0.0003

Data Index: 51227 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0317. Min Act: -0.0003

Data Index: 928934 (C4 (Web Text))

Max Activating Token Index: 50