Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.9227. Min Act: -0.0001

Data Index: 1275195 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.9247. Min Act: -0.0001

Data Index: 964807 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.9451. Min Act: -0.0001

Data Index: 1200019 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.8503. Min Act: -0.0001

Data Index: 668081 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7992. Min Act: -0.0001

Data Index: 147552 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6974. Min Act: -0.0001

Data Index: 1180713 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7212. Min Act: -0.0001

Data Index: 565901 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6899. Min Act: -0.0001

Data Index: 537296 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6350. Min Act: -0.0001

Data Index: 962034 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6617. Min Act: -0.0001

Data Index: 417586 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6484. Min Act: -0.0001

Data Index: 140581 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6983. Min Act: -0.0001

Data Index: 432404 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7098. Min Act: -0.0001

Data Index: 582352 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5540. Min Act: -0.0001

Data Index: 895998 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5524. Min Act: -0.0001

Data Index: 699298 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.4188. Min Act: -0.0001

Data Index: 770816 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5616. Min Act: -0.0001

Data Index: 976553 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6099. Min Act: -0.0001

Data Index: 802285 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5900. Min Act: -0.0001

Data Index: 1281743 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5856. Min Act: -0.0001

Data Index: 347225 (C4 (Web Text))

Max Activating Token Index: 92