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

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

Neuron 4840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.5201. Min Act: -0.0001

Data Index: 1276039 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.2451. Min Act: -0.0001

Data Index: 947827 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.1037. Min Act: -0.0001

Data Index: 777528 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.1821. Min Act: -0.0000

Data Index: 396490 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0998. Min Act: -0.0000

Data Index: 40073 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.1166. Min Act: -0.0001

Data Index: 33970 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0692. Min Act: -0.0001

Data Index: 554023 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1016439 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0690. Min Act: -0.0001

Data Index: 1184411 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0641. Min Act: -0.0001

Data Index: 335661 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9320. Min Act: -0.0001

Data Index: 578208 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1264688 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1345807 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0137. Min Act: -0.0001

Data Index: 265396 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0422. Min Act: -0.0001

Data Index: 129394 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0138. Min Act: -0.0001

Data Index: 1241749 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.8474. Min Act: -0.0001

Data Index: 54865 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0132. Min Act: -0.0001

Data Index: 977774 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9722. Min Act: -0.0001

Data Index: 193882 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0954. Min Act: -0.0000

Data Index: 938303 (C4 (Web Text))

Max Activating Token Index: 477