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

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

Neuron 1471 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4886. Min Act: -0.0000

Data Index: 770600 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1043. Min Act: -0.0000

Data Index: 576936 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0749. Min Act: 0.0001

Data Index: 1079573 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0668. Min Act: -0.0000

Data Index: 953415 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0614. Min Act: -0.0000

Data Index: 41137 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9249. Min Act: -0.0000

Data Index: 241827 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8939. Min Act: -0.0000

Data Index: 14414 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1349421 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8213. Min Act: -0.0000

Data Index: 182336 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7964. Min Act: 0.0000

Data Index: 100665 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8239. Min Act: -0.0000

Data Index: 145790 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8375. Min Act: 0.0000

Data Index: 228457 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8522. Min Act: -0.0000

Data Index: 872600 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8027. Min Act: -0.0000

Data Index: 695307 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7860. Min Act: -0.0000

Data Index: 825491 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7580. Min Act: 0.0000

Data Index: 607562 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1191535 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1023205 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7261. Min Act: 0.0001

Data Index: 1015477 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1254120 (C4 (Web Text))

Max Activating Token Index: 846