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

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

Neuron 3931 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.8807. Min Act: -0.0000

Data Index: 750967 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1314432 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6849. Min Act: -0.0000

Data Index: 267180 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1230288 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1132869 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6327. Min Act: -0.0000

Data Index: 663508 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1208764 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5668. Min Act: -0.0000

Data Index: 222482 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5811. Min Act: -0.0000

Data Index: 474604 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5377. Min Act: -0.0000

Data Index: 646850 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5667. Min Act: -0.0000

Data Index: 621550 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5276. Min Act: -0.0000

Data Index: 717044 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5461. Min Act: -0.0000

Data Index: 882688 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1244535 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5247. Min Act: -0.0000

Data Index: 146311 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5095. Min Act: -0.0000

Data Index: 794062 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5081. Min Act: -0.0000

Data Index: 526362 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.4898. Min Act: -0.0000

Data Index: 662499 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.4874. Min Act: -0.0000

Data Index: 141370 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5032. Min Act: -0.0000

Data Index: 161228 (C4 (Web Text))

Max Activating Token Index: 364