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

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

Neuron 4929 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.7498. Min Act: -0.0000

Data Index: 708317 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.3408. Min Act: -0.0000

Data Index: 130816 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.3851. Min Act: -0.0000

Data Index: 26171 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.4342. Min Act: -0.0000

Data Index: 502921 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.5115. Min Act: -0.0000

Data Index: 620612 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.4652. Min Act: -0.0000

Data Index: 251729 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.3506. Min Act: -0.0000

Data Index: 978362 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.3522. Min Act: -0.0000

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1356968 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1731. Min Act: -0.0000

Data Index: 1255216 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1233961 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1720. Min Act: -0.0000

Data Index: 575561 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1693. Min Act: -0.0000

Data Index: 710653 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.2288. Min Act: -0.0000

Data Index: 270022 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1195. Min Act: -0.0000

Data Index: 762790 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.2626. Min Act: -0.0000

Data Index: 186525 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.2656. Min Act: -0.0000

Data Index: 1064219 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1228707 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1740. Min Act: -0.0000

Data Index: 483390 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 2.7498. Min Range: -2.7498

Max Act: 2.1365. Min Act: -0.0000

Data Index: 1166811 (C4 (Web Text))

Max Activating Token Index: 812