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

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

Neuron 5067 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.2582. Min Act: -0.0002

Data Index: 854971 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0023. Min Act: -0.0002

Data Index: 205451 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9799. Min Act: -0.0002

Data Index: 865000 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9486. Min Act: -0.0002

Data Index: 379674 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9115. Min Act: -0.0002

Data Index: 809662 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8510. Min Act: -0.0002

Data Index: 484451 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8847. Min Act: -0.0002

Data Index: 935959 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9330. Min Act: -0.0002

Data Index: 941005 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9353. Min Act: -0.0002

Data Index: 1093196 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8890. Min Act: -0.0002

Data Index: 227432 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9386. Min Act: -0.0002

Data Index: 437299 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0549. Min Act: -0.0002

Data Index: 70207 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8868. Min Act: -0.0002

Data Index: 1062063 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9176. Min Act: -0.0002

Data Index: 396124 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9910. Min Act: -0.0002

Data Index: 190880 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9864. Min Act: -0.0002

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8927. Min Act: -0.0002

Data Index: 203924 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8898. Min Act: -0.0002

Data Index: 901497 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8244. Min Act: -0.0002

Data Index: 224021 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8696. Min Act: -0.0002

Data Index: 1218850 (C4 (Web Text))

Max Activating Token Index: 508