Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3776 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0002

Data Index: 995563 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0272. Min Act: -0.0003

Data Index: 576057 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0261. Min Act: -0.0003

Data Index: 582456 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1158722 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0243. Min Act: -0.0003

Data Index: 703909 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1070484 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0003

Data Index: 771104 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1102944 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0230. Min Act: -0.0003

Data Index: 895175 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0226. Min Act: -0.0003

Data Index: 885499 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0225. Min Act: -0.0003

Data Index: 832522 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0225. Min Act: -0.0003

Data Index: 670388 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0223. Min Act: -0.0003

Data Index: 917957 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0223. Min Act: -0.0003

Data Index: 701920 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0221. Min Act: -0.0003

Data Index: 886619 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1041249 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0218. Min Act: -0.0003

Data Index: 456340 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0217. Min Act: -0.0003

Data Index: 453083 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1029450 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0219. Min Act: -0.0003

Data Index: 971464 (C4 (Web Text))

Max Activating Token Index: 296