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

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

Neuron 3712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.1406. Min Act: -0.0000

Data Index: 994369 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9941. Min Act: -0.0000

Data Index: 761498 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9774. Min Act: -0.0000

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8959. Min Act: -0.0000

Data Index: 775684 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8904. Min Act: -0.0000

Data Index: 762114 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1072495 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8464. Min Act: 0.0000

Data Index: 1337004 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8952. Min Act: -0.0000

Data Index: 800416 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8409. Min Act: -0.0000

Data Index: 175434 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1202023 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8005. Min Act: -0.0000

Data Index: 70641 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8187. Min Act: -0.0000

Data Index: 108409 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1145780 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8397. Min Act: -0.0000

Data Index: 979264 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8087. Min Act: -0.0000

Data Index: 619867 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.7921. Min Act: -0.0000

Data Index: 323265 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.7678. Min Act: -0.0000

Data Index: 600972 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.7699. Min Act: -0.0000

Data Index: 632370 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.7118. Min Act: -0.0000

Data Index: 229538 (C4 (Web Text))

Max Activating Token Index: 701