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

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

Neuron 2701 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4455. Min Range: -3.4455

Max Act: 3.4455. Min Act: -0.0000

Data Index: 1552652 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.8935. Min Act: -0.0000

Data Index: 1597488 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 3.4455. Min Range: -3.4455

Max Act: 3.1509. Min Act: -0.0000

Data Index: 1480812 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.8731. Min Act: -0.0000

Data Index: 1365430 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 3.4455. Min Range: -3.4455

Max Act: 3.1426. Min Act: -0.0000

Data Index: 1425030 (Python Code)

Max Activating Token Index: 403

Text #5

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.9916. Min Act: -0.0000

Data Index: 1564859 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.9516. Min Act: -0.0000

Data Index: 1529459 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.7490. Min Act: -0.0000

Data Index: 1418905 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.9351. Min Act: -0.0000

Data Index: 1637553 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.7534. Min Act: -0.0000

Data Index: 1535060 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.8882. Min Act: -0.0000

Data Index: 1551919 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.8770. Min Act: -0.0000

Data Index: 1644550 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.4764. Min Act: -0.0000

Data Index: 1475269 (Python Code)

Max Activating Token Index: 698

Text #13

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.9790. Min Act: -0.0000

Data Index: 1470037 (Python Code)

Max Activating Token Index: 254

Text #14

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.7214. Min Act: -0.0000

Data Index: 1610909 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 3.4455. Min Range: -3.4455

Max Act: 3.0508. Min Act: -0.0000

Data Index: 1480545 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1451195 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.5185. Min Act: -0.0000

Data Index: 1395623 (Python Code)

Max Activating Token Index: 435

Text #18

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.6313. Min Act: -0.0000

Data Index: 1553075 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 3.4455. Min Range: -3.4455

Max Act: 2.7447. Min Act: -0.0000

Data Index: 1393187 (Python Code)

Max Activating Token Index: 496