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

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

Neuron 163 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6498. Min Act: -0.0000

Data Index: 150006 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5738. Min Act: -0.0000

Data Index: 851566 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5291. Min Act: -0.0000

Data Index: 19722 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1344199 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1291190 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1064945 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4785. Min Act: -0.0000

Data Index: 863907 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5112. Min Act: -0.0000

Data Index: 98248 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4916. Min Act: -0.0000

Data Index: 931508 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1050612 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4450. Min Act: -0.0000

Data Index: 990840 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1354696 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4576. Min Act: -0.0000

Data Index: 492103 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4425. Min Act: -0.0000

Data Index: 152720 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4540. Min Act: -0.0000

Data Index: 539343 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1149435 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4574. Min Act: -0.0000

Data Index: 15382 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1233273 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4698. Min Act: -0.0000

Data Index: 805617 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4334. Min Act: -0.0000

Data Index: 670930 (C4 (Web Text))

Max Activating Token Index: 943