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

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

Neuron 2986 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1386140 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0860. Min Act: -0.0000

Data Index: 46393 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0184. Min Act: -0.0000

Data Index: 368542 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0603. Min Act: -0.0000

Data Index: 799007 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1344837 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9771. Min Act: -0.0000

Data Index: 452179 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0398. Min Act: -0.0000

Data Index: 350756 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9143. Min Act: -0.0000

Data Index: 949724 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9606. Min Act: -0.0000

Data Index: 12703 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9040. Min Act: -0.0000

Data Index: 493895 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1317745 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1244775 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9249. Min Act: -0.0000

Data Index: 776928 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1303918 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9401. Min Act: -0.0000

Data Index: 678518 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1436851 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.8682. Min Act: -0.0000

Data Index: 297098 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9648. Min Act: -0.0000

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.8508. Min Act: -0.0000

Data Index: 915112 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1648687 (Python Code)

Max Activating Token Index: 188