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

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

Neuron 3478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2409. Min Act: -0.0000

Data Index: 937235 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2115. Min Act: -0.0000

Data Index: 517399 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2190. Min Act: -0.0000

Data Index: 541866 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1978. Min Act: -0.0000

Data Index: 821387 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1134560 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1714. Min Act: -0.0000

Data Index: 121899 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1675. Min Act: -0.0000

Data Index: 112107 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1713. Min Act: -0.0001

Data Index: 463966 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1710. Min Act: -0.0000

Data Index: 540391 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1143711 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1681. Min Act: -0.0001

Data Index: 201963 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1817. Min Act: -0.0000

Data Index: 347387 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1594. Min Act: -0.0001

Data Index: 498132 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1721. Min Act: -0.0000

Data Index: 615464 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1655. Min Act: -0.0000

Data Index: 285678 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1658. Min Act: -0.0000

Data Index: 970271 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1703. Min Act: -0.0000

Data Index: 637631 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1521. Min Act: -0.0001

Data Index: 923191 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1675. Min Act: -0.0000

Data Index: 587288 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1614. Min Act: -0.0000

Data Index: 551850 (C4 (Web Text))

Max Activating Token Index: 238