Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1993 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0005

Data Index: 59148 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0270. Min Act: -0.0005

Data Index: 622430 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0281. Min Act: -0.0005

Data Index: 410931 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0261. Min Act: -0.0005

Data Index: 60395 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1163696 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0252. Min Act: -0.0005

Data Index: 231573 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0248. Min Act: -0.0005

Data Index: 114161 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0246. Min Act: -0.0005

Data Index: 227704 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0245. Min Act: -0.0005

Data Index: 893486 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0243. Min Act: -0.0005

Data Index: 76536 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1208594 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1255217 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0239. Min Act: -0.0005

Data Index: 870777 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0246. Min Act: -0.0005

Data Index: 994776 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0233. Min Act: -0.0005

Data Index: 494831 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0239. Min Act: -0.0005

Data Index: 535921 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0239. Min Act: -0.0005

Data Index: 495991 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0237. Min Act: -0.0005

Data Index: 560750 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0237. Min Act: -0.0005

Data Index: 941651 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0242. Min Act: -0.0005

Data Index: 159434 (C4 (Web Text))

Max Activating Token Index: 99