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

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

Neuron 2592 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0003

Data Index: 576001 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0377. Min Act: -0.0003

Data Index: 49403 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1204464 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0374. Min Act: -0.0003

Data Index: 410345 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1068264 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0332. Min Act: -0.0003

Data Index: 594459 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0329. Min Act: -0.0003

Data Index: 319472 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1014573 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1247671 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1348142 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0313. Min Act: -0.0003

Data Index: 756847 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1321124 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0320. Min Act: -0.0003

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0323. Min Act: -0.0003

Data Index: 146782 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0304. Min Act: -0.0003

Data Index: 49844 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0342. Min Act: -0.0003

Data Index: 763849 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0305. Min Act: -0.0003

Data Index: 784465 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0314. Min Act: -0.0003

Data Index: 68082 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0300. Min Act: -0.0003

Data Index: 894596 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0325. Min Act: -0.0003

Data Index: 363853 (C4 (Web Text))

Max Activating Token Index: 205