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

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

Neuron 4661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.7031. Min Act: -0.0000

Data Index: 900965 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.3126. Min Act: -0.0000

Data Index: 291852 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.2608. Min Act: -0.0000

Data Index: 615871 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1528574 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.2349. Min Act: -0.0000

Data Index: 385636 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1312055 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.1689. Min Act: -0.0000

Data Index: 812615 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.1302. Min Act: -0.0000

Data Index: 486714 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.3559. Min Act: -0.0000

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.2168. Min Act: -0.0000

Data Index: 499315 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0837. Min Act: -0.0000

Data Index: 810533 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.1829. Min Act: -0.0000

Data Index: 781432 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1303490 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0598. Min Act: -0.0000

Data Index: 743412 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.1250. Min Act: -0.0000

Data Index: 854602 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.1258. Min Act: -0.0000

Data Index: 441314 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0144. Min Act: -0.0000

Data Index: 186866 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1262533 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 2.7031. Min Range: -2.7031

Max Act: 2.0628. Min Act: -0.0000

Data Index: 358247 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 2.7031. Min Range: -2.7031

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1154420 (C4 (Web Text))

Max Activating Token Index: 895