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

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

Neuron 5357 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: 1.1604. Min Range: -1.1604

Max Act: 1.1604. Min Act: -0.0000

Data Index: 890083 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0204. Min Act: -0.0000

Data Index: 211010 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1216057 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8982. Min Act: -0.0000

Data Index: 482640 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7435. Min Act: -0.0000

Data Index: 442771 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5446. Min Act: -0.0000

Data Index: 594952 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1087608 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5268. Min Act: -0.0000

Data Index: 549372 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4950. Min Act: -0.0000

Data Index: 12119 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5163. Min Act: -0.0000

Data Index: 723724 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4920. Min Act: -0.0000

Data Index: 383021 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5232. Min Act: -0.0000

Data Index: 573370 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5158. Min Act: 0.0000

Data Index: 91127 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4990. Min Act: -0.0000

Data Index: 774996 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1654723 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5189. Min Act: -0.0000

Data Index: 808824 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1326362 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4834. Min Act: -0.0000

Data Index: 790742 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4786. Min Act: -0.0000

Data Index: 44671 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1330932 (C4 (Web Text))

Max Activating Token Index: 1022