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

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

Neuron 2814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1197902 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7639. Min Act: -0.0000

Data Index: 649101 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7510. Min Act: -0.0000

Data Index: 202961 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1056519 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6869. Min Act: -0.0000

Data Index: 9543 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1259669 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6722. Min Act: -0.0000

Data Index: 949000 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6227. Min Act: -0.0000

Data Index: 747563 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6699. Min Act: -0.0000

Data Index: 934153 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1006072 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6448. Min Act: -0.0000

Data Index: 936203 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6321. Min Act: -0.0000

Data Index: 347233 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6687. Min Act: -0.0000

Data Index: 77457 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6124. Min Act: -0.0000

Data Index: 66953 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5912. Min Act: -0.0000

Data Index: 717930 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5901. Min Act: -0.0000

Data Index: 979933 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6244. Min Act: -0.0000

Data Index: 154290 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6580. Min Act: -0.0000

Data Index: 94242 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5774. Min Act: -0.0000

Data Index: 74426 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5875. Min Act: -0.0000

Data Index: 160350 (C4 (Web Text))

Max Activating Token Index: 33