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

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

Neuron 678 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: 2.0653. Min Range: -2.0653

Max Act: 2.0653. Min Act: -0.0000

Data Index: 1084502 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9659. Min Act: -0.0000

Data Index: 1268727 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.6124. Min Act: -0.0000

Data Index: 596916 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.2436. Min Act: -0.0000

Data Index: 552209 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.2442. Min Act: -0.0000

Data Index: 585599 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.3359. Min Act: -0.0000

Data Index: 121792 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.2429. Min Act: -0.0000

Data Index: 155472 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.0822. Min Act: -0.0000

Data Index: 623464 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.0758. Min Act: -0.0000

Data Index: 451061 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1906. Min Act: -0.0000

Data Index: 960562 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1154122 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1922. Min Act: -0.0000

Data Index: 533578 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1829. Min Act: -0.0000

Data Index: 586314 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1195. Min Act: -0.0000

Data Index: 335845 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1152582 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1682. Min Act: -0.0000

Data Index: 650868 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.3179. Min Act: -0.0000

Data Index: 657051 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1574. Min Act: -0.0000

Data Index: 626882 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1151421 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1246050 (C4 (Web Text))

Max Activating Token Index: 77