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

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

Neuron 752 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: 1.6135. Min Range: -1.6135

Max Act: 1.6135. Min Act: -0.0000

Data Index: 462994 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1221424 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4578. Min Act: -0.0000

Data Index: 538213 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.3029. Min Act: -0.0000

Data Index: 875696 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1261882 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1900. Min Act: -0.0000

Data Index: 391444 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1694. Min Act: -0.0000

Data Index: 65112 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.6135. Min Range: -1.6135

Max Act: 0.9967. Min Act: -0.0000

Data Index: 597072 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.2639. Min Act: -0.0000

Data Index: 218433 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1554718 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1247666 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1776. Min Act: -0.0000

Data Index: 217585 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.0437. Min Act: -0.0000

Data Index: 13478 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.0918. Min Act: -0.0000

Data Index: 60796 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.0949. Min Act: -0.0000

Data Index: 671341 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.0733. Min Act: -0.0000

Data Index: 896407 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1998. Min Act: -0.0000

Data Index: 779726 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1501. Min Act: -0.0000

Data Index: 637861 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1133. Min Act: -0.0000

Data Index: 482844 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.1024. Min Act: -0.0000

Data Index: 73415 (C4 (Web Text))

Max Activating Token Index: 254