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

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

Neuron 1740 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8895. Min Act: -0.0001

Data Index: 374006 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.9288. Min Act: -0.0000

Data Index: 169732 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1264344 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8234. Min Act: -0.0000

Data Index: 457069 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8222. Min Act: -0.0000

Data Index: 557452 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7849. Min Act: -0.0000

Data Index: 577325 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7067. Min Act: -0.0000

Data Index: 127172 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1142184 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7641. Min Act: -0.0000

Data Index: 31784 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7281. Min Act: -0.0000

Data Index: 587306 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1016302 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7381. Min Act: -0.0000

Data Index: 835740 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7426. Min Act: -0.0001

Data Index: 981102 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7113. Min Act: -0.0000

Data Index: 492030 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7044. Min Act: -0.0000

Data Index: 40942 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.6954. Min Act: -0.0000

Data Index: 541711 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.6965. Min Act: -0.0000

Data Index: 269702 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1192532 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7032. Min Act: -0.0000

Data Index: 669568 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.6737. Min Act: -0.0001

Data Index: 385983 (C4 (Web Text))

Max Activating Token Index: 48