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

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

Neuron 1930 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: 1.0463. Min Range: -1.0463

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1463790 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1386234 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1650693 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1215938 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1636705 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6895. Min Act: -0.0000

Data Index: 241072 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1070094 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6983. Min Act: -0.0000

Data Index: 684392 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1233316 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6356. Min Act: -0.0000

Data Index: 508477 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1310064 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6124. Min Act: -0.0000

Data Index: 476050 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1206554 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6343. Min Act: -0.0000

Data Index: 568180 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6229. Min Act: -0.0000

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6388. Min Act: -0.0000

Data Index: 390982 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.5553. Min Act: -0.0000

Data Index: 927291 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.5228. Min Act: -0.0000

Data Index: 921796 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6039. Min Act: -0.0000

Data Index: 904170 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.0463. Min Range: -1.0463

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1554529 (Python Code)

Max Activating Token Index: 625