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

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

Neuron 3557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2673. Min Act: -0.0002

Data Index: 313146 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2439. Min Act: -0.0002

Data Index: 990540 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2404. Min Act: -0.0002

Data Index: 1102830 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2289. Min Act: -0.0002

Data Index: 463600 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2342. Min Act: -0.0002

Data Index: 156030 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2332. Min Act: -0.0002

Data Index: 530523 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2221. Min Act: -0.0002

Data Index: 1090464 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2487. Min Act: -0.0002

Data Index: 294080 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2275. Min Act: -0.0002

Data Index: 1051386 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2334. Min Act: -0.0002

Data Index: 903921 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2157. Min Act: -0.0002

Data Index: 404619 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2197. Min Act: -0.0002

Data Index: 345768 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2154. Min Act: -0.0002

Data Index: 288694 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2172. Min Act: -0.0002

Data Index: 138690 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2226. Min Act: -0.0002

Data Index: 1165103 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2137. Min Act: -0.0002

Data Index: 741635 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2072. Min Act: -0.0002

Data Index: 342950 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2030. Min Act: -0.0002

Data Index: 971318 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1922. Min Act: -0.0002

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2022. Min Act: -0.0002

Data Index: 1300567 (C4 (Web Text))

Max Activating Token Index: 738