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

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

Neuron 3609 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.3222. Min Act: -0.0000

Data Index: 514313 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.8457. Min Act: -0.0000

Data Index: 572207 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.8415. Min Act: -0.0000

Data Index: 368827 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0408. Min Act: -0.0000

Data Index: 322483 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.8603. Min Act: -0.0000

Data Index: 301719 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.8308. Min Act: -0.0000

Data Index: 677603 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.7928. Min Act: -0.0000

Data Index: 223272 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.7259. Min Act: -0.0000

Data Index: 997777 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6479. Min Act: -0.0000

Data Index: 400129 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1297975 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.7557. Min Act: -0.0000

Data Index: 342729 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1645248 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1393833 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1504756 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1523631 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1638979 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6332. Min Act: -0.0000

Data Index: 997739 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6099. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.3222. Min Range: -1.3222

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1613846 (Python Code)

Max Activating Token Index: 249