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

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

Neuron 4736 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: 1.1491. Min Range: -1.1491

Max Act: 1.1491. Min Act: -0.0001

Data Index: 1200393 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.1491. Min Range: -1.1491

Max Act: 1.0334. Min Act: -0.0001

Data Index: 837518 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8980. Min Act: -0.0001

Data Index: 364974 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.9165. Min Act: -0.0001

Data Index: 766890 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8295. Min Act: -0.0001

Data Index: 1215016 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8250. Min Act: -0.0001

Data Index: 220322 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7633. Min Act: -0.0001

Data Index: 424418 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7946. Min Act: -0.0001

Data Index: 758412 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1110578 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7314. Min Act: -0.0001

Data Index: 484301 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1216084 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7291. Min Act: -0.0001

Data Index: 353521 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7239. Min Act: -0.0001

Data Index: 14974 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6108. Min Act: -0.0001

Data Index: 744649 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1040488 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6425. Min Act: -0.0001

Data Index: 9201 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6938. Min Act: -0.0001

Data Index: 359516 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6682. Min Act: -0.0001

Data Index: 759738 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6193. Min Act: -0.0001

Data Index: 995274 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6725. Min Act: -0.0001

Data Index: 519140 (C4 (Web Text))

Max Activating Token Index: 96