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

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

Neuron 92 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1201. Min Range: -2.1201

Max Act: 2.1201. Min Act: -0.0000

Data Index: 1221735 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.1201. Min Range: -2.1201

Max Act: 2.0112. Min Act: -0.0001

Data Index: 656301 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.9231. Min Act: -0.0000

Data Index: 616509 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.7530. Min Act: -0.0000

Data Index: 562438 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1313432 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1060585 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.4029. Min Act: -0.0000

Data Index: 521180 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1061464 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.1201. Min Range: -2.1201

Max Act: 1.1065. Min Act: -0.0001

Data Index: 878811 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9954. Min Act: -0.0000

Data Index: 392780 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9736. Min Act: -0.0000

Data Index: 110747 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9038. Min Act: -0.0000

Data Index: 488176 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9295. Min Act: -0.0001

Data Index: 997762 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.8388. Min Act: -0.0001

Data Index: 730855 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9160. Min Act: -0.0000

Data Index: 27470 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9094. Min Act: -0.0000

Data Index: 213458 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.8784. Min Act: -0.0000

Data Index: 224051 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1052206 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.8705. Min Act: -0.0000

Data Index: 158867 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 2.1201. Min Range: -2.1201

Max Act: 0.9167. Min Act: -0.0000

Data Index: 726031 (C4 (Web Text))

Max Activating Token Index: 548