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

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

Neuron 1821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0343. Min Act: -0.0003

Data Index: 1105220 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0490. Min Act: -0.0003

Data Index: 246238 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0343. Min Act: -0.0003

Data Index: 504795 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9278. Min Act: -0.0002

Data Index: 404563 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9446. Min Act: -0.0003

Data Index: 1336847 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9226. Min Act: -0.0002

Data Index: 362417 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8862. Min Act: -0.0003

Data Index: 176545 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8805. Min Act: -0.0003

Data Index: 1226037 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8864. Min Act: -0.0002

Data Index: 960896 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8928. Min Act: -0.0003

Data Index: 1217783 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8715. Min Act: -0.0003

Data Index: 101530 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9025. Min Act: -0.0003

Data Index: 657374 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8488. Min Act: -0.0003

Data Index: 759870 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8688. Min Act: -0.0003

Data Index: 500814 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8992. Min Act: -0.0003

Data Index: 513198 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8378. Min Act: -0.0002

Data Index: 561633 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8624. Min Act: -0.0003

Data Index: 927272 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8570. Min Act: -0.0003

Data Index: 710956 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8586. Min Act: -0.0003

Data Index: 727153 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8532. Min Act: -0.0002

Data Index: 1171538 (C4 (Web Text))

Max Activating Token Index: 462