Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2185 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.7472. Min Act: -0.0000

Data Index: 1245268 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.7044. Min Act: -0.0000

Data Index: 487931 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4857. Min Act: -0.0000

Data Index: 879329 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.5259. Min Act: -0.0000

Data Index: 791419 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4463. Min Act: -0.0000

Data Index: 202257 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4646. Min Act: -0.0000

Data Index: 1270348 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4327. Min Act: -0.0000

Data Index: 432745 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4490. Min Act: -0.0000

Data Index: 824540 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1235378 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1205968 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.4071. Min Act: -0.0000

Data Index: 408648 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.3597. Min Act: -0.0000

Data Index: 49799 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2396. Min Act: -0.0000

Data Index: 474379 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2503. Min Act: -0.0000

Data Index: 884661 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2426. Min Act: -0.0000

Data Index: 13583 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1149056 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1334356 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2978. Min Act: -0.0000

Data Index: 171503 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.2674. Min Act: -0.0000

Data Index: 476145 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.7472. Min Range: -1.7472

Max Act: 1.1266. Min Act: -0.0000

Data Index: 234848 (C4 (Web Text))

Max Activating Token Index: 941