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

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

Neuron 1892 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: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0001

Data Index: 264311 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0235. Min Act: -0.0001

Data Index: 16031 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0228. Min Act: -0.0001

Data Index: 437012 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1390223 (Python Code)

Max Activating Token Index: 952

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0226. Min Act: -0.0001

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1194185 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0225. Min Act: -0.0001

Data Index: 964356 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0220. Min Act: -0.0001

Data Index: 321606 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1469763 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1167792 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0218. Min Act: -0.0001

Data Index: 557467 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0219. Min Act: -0.0001

Data Index: 840797 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1555223 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0212. Min Act: -0.0001

Data Index: 640054 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1310721 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1200883 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0001

Data Index: 964496 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0001

Data Index: 26175 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1494086 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0210. Min Act: -0.0001

Data Index: 407228 (C4 (Web Text))

Max Activating Token Index: 600