Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 132 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0014. Min Range: -1.0014

Max Act: 1.0014. Min Act: -0.0004

Data Index: 917376 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9755. Min Act: -0.0004

Data Index: 1281533 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8649. Min Act: -0.0004

Data Index: 881877 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8438. Min Act: -0.0004

Data Index: 736133 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8618. Min Act: -0.0004

Data Index: 841008 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8472. Min Act: -0.0004

Data Index: 322426 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8701. Min Act: -0.0004

Data Index: 1205110 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8351. Min Act: -0.0004

Data Index: 1282526 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8040. Min Act: -0.0004

Data Index: 389434 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7951. Min Act: -0.0004

Data Index: 726982 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7331. Min Act: -0.0004

Data Index: 261434 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8158. Min Act: -0.0004

Data Index: 846589 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8508. Min Act: -0.0004

Data Index: 656511 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8222. Min Act: -0.0004

Data Index: 981023 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7543. Min Act: -0.0004

Data Index: 1046888 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8190. Min Act: -0.0004

Data Index: 1047323 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7280. Min Act: -0.0004

Data Index: 755037 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8143. Min Act: -0.0004

Data Index: 1018696 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.6927. Min Act: -0.0004

Data Index: 152365 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7818. Min Act: -0.0004

Data Index: 421191 (C4 (Web Text))

Max Activating Token Index: 734