Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1175311 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1187998 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1353284 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1990. Min Act: -0.0000

Data Index: 712370 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1092178 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1255378 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1774. Min Act: -0.0001

Data Index: 751351 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1674. Min Act: -0.0001

Data Index: 262643 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1015207 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1616. Min Act: -0.0001

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1659. Min Act: -0.0001

Data Index: 198217 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1678. Min Act: -0.0001

Data Index: 1525729 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1213651 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1042349 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1602. Min Act: -0.0000

Data Index: 642434 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1279090 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1550. Min Act: -0.0001

Data Index: 576501 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1711. Min Act: -0.0001

Data Index: 215525 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1528. Min Act: -0.0000

Data Index: 558844 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1458. Min Act: -0.0000

Data Index: 794315 (C4 (Web Text))

Max Activating Token Index: 440