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

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

Neuron 4247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.6230. Min Act: -0.0001

Data Index: 349197 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.4617. Min Act: -0.0001

Data Index: 947537 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.5642. Min Act: -0.0001

Data Index: 1183003 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.3422. Min Act: -0.0001

Data Index: 75482 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.5685. Min Act: -0.0001

Data Index: 174549 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.5010. Min Act: -0.0001

Data Index: 947734 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.5281. Min Act: -0.0001

Data Index: 702128 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.1538. Min Act: -0.0001

Data Index: 1318182 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.2138. Min Act: -0.0001

Data Index: 68775 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.8383. Min Act: -0.0001

Data Index: 76827 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.8836. Min Act: -0.0001

Data Index: 882835 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.1650. Min Act: -0.0001

Data Index: 1304464 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.9042. Min Act: -0.0001

Data Index: 349672 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.6022. Min Act: -0.0001

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.1961. Min Act: -0.0001

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 3.6230. Min Range: -3.6230

Max Act: 3.0305. Min Act: -0.0001

Data Index: 313466 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.9650. Min Act: -0.0001

Data Index: 1030515 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.5433. Min Act: -0.0001

Data Index: 848710 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.6388. Min Act: -0.0001

Data Index: 103462 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 3.6230. Min Range: -3.6230

Max Act: 2.8983. Min Act: -0.0001

Data Index: 648449 (C4 (Web Text))

Max Activating Token Index: 264