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

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

Neuron 2142 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0231. Min Range: -1.0231

Max Act: 1.0231. Min Act: -0.0001

Data Index: 1000687 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.0231. Min Range: -1.0231

Max Act: 1.0073. Min Act: -0.0001

Data Index: 393587 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9945. Min Act: -0.0001

Data Index: 777553 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1076259 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8574. Min Act: -0.0001

Data Index: 134180 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1267505 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7696. Min Act: -0.0001

Data Index: 234349 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7715. Min Act: -0.0001

Data Index: 105796 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7534. Min Act: -0.0001

Data Index: 364567 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7552. Min Act: -0.0001

Data Index: 474296 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6887. Min Act: -0.0001

Data Index: 1339551 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1240972 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1056828 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6672. Min Act: -0.0001

Data Index: 83870 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6466. Min Act: -0.0001

Data Index: 365846 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1008810 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6456. Min Act: -0.0001

Data Index: 714047 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6367. Min Act: -0.0001

Data Index: 897204 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6416. Min Act: -0.0001

Data Index: 484660 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1180525 (C4 (Web Text))

Max Activating Token Index: 400