Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2015 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.9181. Min Act: -0.0001

Data Index: 873469 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8173. Min Act: -0.0001

Data Index: 903898 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.9320. Min Act: -0.0002

Data Index: 984525 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8303. Min Act: -0.0002

Data Index: 136015 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7998. Min Act: -0.0002

Data Index: 235237 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.9934. Min Act: -0.0002

Data Index: 1319747 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8467. Min Act: -0.0002

Data Index: 748399 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8114. Min Act: -0.0002

Data Index: 223642 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8811. Min Act: -0.0002

Data Index: 402315 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7882. Min Act: -0.0002

Data Index: 245176 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8114. Min Act: -0.0002

Data Index: 390387 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7855. Min Act: -0.0002

Data Index: 930783 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7408. Min Act: -0.0001

Data Index: 185278 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.8287. Min Act: -0.0002

Data Index: 451411 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7695. Min Act: -0.0001

Data Index: 187048 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7724. Min Act: -0.0002

Data Index: 161747 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7827. Min Act: -0.0002

Data Index: 464938 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7684. Min Act: -0.0002

Data Index: 1127077 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7343. Min Act: -0.0002

Data Index: 851764 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.9934. Min Range: -0.9934

Max Act: 0.7141. Min Act: -0.0002

Data Index: 132057 (C4 (Web Text))

Max Activating Token Index: 995