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

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

Neuron 3740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6763. Min Act: -0.0001

Data Index: 392290 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1201967 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6193. Min Act: -0.0001

Data Index: 262334 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6139. Min Act: -0.0001

Data Index: 316853 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6474. Min Act: -0.0001

Data Index: 305596 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5590. Min Act: -0.0001

Data Index: 436916 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1148072 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5448. Min Act: -0.0001

Data Index: 625009 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5719. Min Act: -0.0001

Data Index: 921106 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5919. Min Act: -0.0001

Data Index: 928070 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5919. Min Act: -0.0001

Data Index: 1071733 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5919. Min Act: -0.0001

Data Index: 432039 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5579. Min Act: -0.0001

Data Index: 151368 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6075. Min Act: -0.0001

Data Index: 557663 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1100236 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5374. Min Act: -0.0001

Data Index: 896186 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5444. Min Act: -0.0001

Data Index: 571270 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5254. Min Act: -0.0001

Data Index: 1159894 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1122835 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5607. Min Act: -0.0001

Data Index: 861541 (C4 (Web Text))

Max Activating Token Index: 346