Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1892 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0401. Min Act: -0.0001

Data Index: 911067 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0001

Data Index: 706873 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0392. Min Act: -0.0002

Data Index: 833329 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1011500 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1342683 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0354. Min Act: -0.0001

Data Index: 179009 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0362. Min Act: -0.0002

Data Index: 637465 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1537516 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1206841 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0366. Min Act: -0.0002

Data Index: 836245 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0321. Min Act: -0.0002

Data Index: 924129 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1336758 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0342. Min Act: -0.0001

Data Index: 955503 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0351. Min Act: -0.0002

Data Index: 276991 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0320. Min Act: -0.0001

Data Index: 478447 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0334. Min Act: -0.0002

Data Index: 403951 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0343. Min Act: -0.0001

Data Index: 276468 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0350. Min Act: -0.0001

Data Index: 978205 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1015407 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0316. Min Act: -0.0001

Data Index: 867934 (C4 (Web Text))

Max Activating Token Index: 73