Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 606 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1188422 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2544. Min Act: -0.0001

Data Index: 119208 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2459. Min Act: -0.0001

Data Index: 847003 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2436. Min Act: -0.0001

Data Index: 737028 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1084104 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1046702 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1001067 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2287. Min Act: -0.0001

Data Index: 808904 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2370. Min Act: -0.0001

Data Index: 156392 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1355962 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2318. Min Act: -0.0001

Data Index: 730975 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2231. Min Act: -0.0001

Data Index: 718402 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2226. Min Act: -0.0001

Data Index: 169860 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2111. Min Act: -0.0001

Data Index: 575914 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2149. Min Act: -0.0001

Data Index: 952682 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2112. Min Act: -0.0001

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2090. Min Act: -0.0001

Data Index: 527337 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1064850 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.2073. Min Act: -0.0001

Data Index: 667354 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.2674. Min Range: -0.2674

Max Act: 0.1984. Min Act: -0.0001

Data Index: 494754 (C4 (Web Text))

Max Activating Token Index: 310