Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.3271. Min Act: -0.0000

Data Index: 681635 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.8782. Min Act: -0.0000

Data Index: 1125357 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.6664. Min Act: -0.0000

Data Index: 372524 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.6900. Min Act: -0.0000

Data Index: 617591 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.4239. Min Act: -0.0000

Data Index: 144481 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.5269. Min Act: -0.0000

Data Index: 290558 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.4822. Min Act: -0.0000

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.2764. Min Act: -0.0000

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.3660. Min Act: -0.0000

Data Index: 527761 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.3511. Min Act: -0.0000

Data Index: 1085031 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.2141. Min Act: -0.0001

Data Index: 367422 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.1818. Min Act: -0.0000

Data Index: 640784 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.2964. Min Act: -0.0000

Data Index: 1583407 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.1651. Min Act: -0.0000

Data Index: 1284028 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.1431. Min Act: -0.0000

Data Index: 911142 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.0235. Min Act: -0.0000

Data Index: 276413 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.1245. Min Act: -0.0000

Data Index: 1193785 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.2073. Min Act: -0.0000

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.3271. Min Range: -3.3271

Max Act: 2.0862. Min Act: -0.0000

Data Index: 815971 (C4 (Web Text))

Max Activating Token Index: 808