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

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

Neuron 4907 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: 1.1112. Min Range: -1.1112

Max Act: 1.1112. Min Act: -0.0000

Data Index: 361626 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0521. Min Act: -0.0000

Data Index: 943413 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1258635 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0228. Min Act: -0.0000

Data Index: 765222 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0855. Min Act: -0.0000

Data Index: 338797 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0039. Min Act: -0.0000

Data Index: 243820 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9684. Min Act: -0.0000

Data Index: 900668 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0131. Min Act: -0.0000

Data Index: 358546 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9388. Min Act: -0.0000

Data Index: 124636 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9953. Min Act: -0.0000

Data Index: 746255 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0072. Min Act: -0.0000

Data Index: 635419 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9494. Min Act: -0.0000

Data Index: 645660 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1264272 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1059567 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9327. Min Act: -0.0000

Data Index: 851252 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8699. Min Act: -0.0000

Data Index: 797206 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1105490 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8910. Min Act: -0.0000

Data Index: 756547 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1149768 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1261740 (C4 (Web Text))

Max Activating Token Index: 554