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

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

Neuron 5543 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0001

Data Index: 138268 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0239. Min Act: -0.0001

Data Index: 327079 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1227533 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1018400 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1233678 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0216. Min Act: -0.0001

Data Index: 16257 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1277558 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0209. Min Act: -0.0001

Data Index: 65230 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0204. Min Act: -0.0001

Data Index: 972715 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0203. Min Act: -0.0001

Data Index: 573497 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0203. Min Act: -0.0001

Data Index: 921285 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1007929 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1061650 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0198. Min Act: -0.0001

Data Index: 337056 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0199. Min Act: -0.0001

Data Index: 979985 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1285562 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0198. Min Act: -0.0002

Data Index: 340289 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0196. Min Act: -0.0001

Data Index: 214511 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0197. Min Act: -0.0001

Data Index: 757100 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0195. Min Act: -0.0001

Data Index: 785657 (C4 (Web Text))

Max Activating Token Index: 160