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

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

Neuron 1903 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: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1048594 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0482. Min Act: -0.0001

Data Index: 486465 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0462. Min Act: -0.0001

Data Index: 270907 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0441. Min Act: -0.0001

Data Index: 391689 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0345. Min Act: -0.0002

Data Index: 341028 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0473. Min Act: -0.0001

Data Index: 541743 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0520. Min Act: -0.0001

Data Index: 948522 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1290506 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0403. Min Act: -0.0001

Data Index: 778815 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0482. Min Act: -0.0002

Data Index: 400040 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0369. Min Act: -0.0001

Data Index: 340111 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1329664 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0331. Min Act: -0.0001

Data Index: 560484 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0290. Min Act: -0.0001

Data Index: 22046 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0307. Min Act: -0.0001

Data Index: 30824 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0349. Min Act: -0.0001

Data Index: 585020 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1331380 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0319. Min Act: -0.0002

Data Index: 83659 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0339. Min Act: -0.0001

Data Index: 886450 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0304. Min Act: -0.0001

Data Index: 107322 (C4 (Web Text))

Max Activating Token Index: 966