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

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

Neuron 6117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3306. Min Act: -0.0002

Data Index: 913253 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3301. Min Act: -0.0002

Data Index: 1276635 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3213. Min Act: -0.0002

Data Index: 15249 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2915. Min Act: -0.0002

Data Index: 1465897 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2872. Min Act: -0.0002

Data Index: 213631 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2828. Min Act: -0.0002

Data Index: 322235 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2831. Min Act: -0.0002

Data Index: 901756 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2835. Min Act: -0.0002

Data Index: 66936 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2799. Min Act: -0.0002

Data Index: 1405390 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2894. Min Act: -0.0002

Data Index: 1327024 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2799. Min Act: -0.0002

Data Index: 171092 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2782. Min Act: -0.0002

Data Index: 789585 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2730. Min Act: -0.0002

Data Index: 1167839 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2771. Min Act: -0.0002

Data Index: 26762 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2687. Min Act: -0.0002

Data Index: 1013358 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2732. Min Act: -0.0002

Data Index: 1138730 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2629. Min Act: -0.0002

Data Index: 218599 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2713. Min Act: -0.0002

Data Index: 385117 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2659. Min Act: -0.0002

Data Index: 773903 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2619. Min Act: -0.0002

Data Index: 376992 (C4 (Web Text))

Max Activating Token Index: 449