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

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

Neuron 195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3603. Min Act: -0.0001

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1077218 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1283481 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3724. Min Act: -0.0001

Data Index: 226079 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1251188 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3431. Min Act: -0.0000

Data Index: 479156 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3344. Min Act: -0.0001

Data Index: 183705 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3571. Min Act: -0.0001

Data Index: 365352 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1339323 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3158. Min Act: -0.0000

Data Index: 482838 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3386. Min Act: -0.0001

Data Index: 205039 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3381. Min Act: -0.0001

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1134320 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3242. Min Act: -0.0000

Data Index: 610112 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3468. Min Act: -0.0000

Data Index: 814570 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3236. Min Act: -0.0001

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3428. Min Act: -0.0001

Data Index: 79153 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3444. Min Act: -0.0000

Data Index: 97842 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3540. Min Act: -0.0001

Data Index: 77639 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3399. Min Act: -0.0001

Data Index: 632530 (C4 (Web Text))

Max Activating Token Index: 835