Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 829 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 849094 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0670. Min Act: -0.0002

Data Index: 72508 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0622. Min Act: -0.0002

Data Index: 492630 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1004139 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1118170 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0604. Min Act: -0.0002

Data Index: 525291 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0583. Min Act: -0.0002

Data Index: 89879 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0594. Min Act: -0.0002

Data Index: 353025 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0612. Min Act: -0.0002

Data Index: 848724 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0599. Min Act: -0.0002

Data Index: 840761 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1280335 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0599. Min Act: -0.0002

Data Index: 625873 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0598. Min Act: -0.0002

Data Index: 475239 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1039678 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0557. Min Act: -0.0002

Data Index: 198337 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0617. Min Act: -0.0002

Data Index: 335979 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0616. Min Act: -0.0002

Data Index: 838005 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0579. Min Act: -0.0002

Data Index: 82755 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0549. Min Act: -0.0002

Data Index: 271836 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0565. Min Act: -0.0002

Data Index: 80958 (C4 (Web Text))

Max Activating Token Index: 557