Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4973 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.4031. Min Act: -0.0001

Data Index: 1336925 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2734. Min Act: -0.0001

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2164. Min Act: -0.0001

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2559. Min Act: -0.0001

Data Index: 439311 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1215. Min Act: -0.0001

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1346135 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0002. Min Act: -0.0001

Data Index: 710105 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1212961 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9952. Min Act: -0.0001

Data Index: 557051 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9266. Min Act: -0.0001

Data Index: 1090363 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8304. Min Act: -0.0001

Data Index: 721862 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9594. Min Act: -0.0001

Data Index: 326110 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1293011 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1107330 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9275. Min Act: -0.0001

Data Index: 147404 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8499. Min Act: -0.0001

Data Index: 522415 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8052. Min Act: -0.0001

Data Index: 903688 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8839. Min Act: -0.0001

Data Index: 593762 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8511. Min Act: -0.0001

Data Index: 879046 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.8188. Min Act: -0.0001

Data Index: 502209 (C4 (Web Text))

Max Activating Token Index: 938