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

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

Neuron 472 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: 1.2322. Min Range: -1.2322

Max Act: 1.1684. Min Act: -0.0002

Data Index: 545483 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.2322. Min Act: -0.0002

Data Index: 925580 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0924. Min Act: -0.0002

Data Index: 373703 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0232. Min Act: -0.0002

Data Index: 133025 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0046. Min Act: -0.0002

Data Index: 205887 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9992. Min Act: -0.0002

Data Index: 400885 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9089. Min Act: -0.0002

Data Index: 503486 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0279. Min Act: -0.0002

Data Index: 860129 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9518. Min Act: -0.0002

Data Index: 139217 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1091. Min Act: -0.0002

Data Index: 547174 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0814. Min Act: -0.0002

Data Index: 679284 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0086. Min Act: -0.0002

Data Index: 34508 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9253. Min Act: -0.0002

Data Index: 609573 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9195. Min Act: -0.0002

Data Index: 1192977 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9749. Min Act: -0.0002

Data Index: 290937 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.8838. Min Act: -0.0002

Data Index: 3682 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.8438. Min Act: -0.0002

Data Index: 58404 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9229. Min Act: -0.0002

Data Index: 470672 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.8062. Min Act: -0.0002

Data Index: 1213661 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.8905. Min Act: -0.0002

Data Index: 341841 (C4 (Web Text))

Max Activating Token Index: 460