Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.3234. Min Act: -0.0001

Data Index: 486191 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.2172. Min Act: -0.0001

Data Index: 116180 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.1256. Min Act: -0.0001

Data Index: 130565 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0911. Min Act: -0.0001

Data Index: 1264725 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0747. Min Act: -0.0001

Data Index: 365516 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0607. Min Act: -0.0001

Data Index: 385606 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0831. Min Act: -0.0001

Data Index: 1207296 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0595. Min Act: -0.0001

Data Index: 567085 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0611. Min Act: -0.0001

Data Index: 237378 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9850. Min Act: -0.0001

Data Index: 426932 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0149. Min Act: -0.0001

Data Index: 125127 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9723. Min Act: -0.0001

Data Index: 1065603 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0305. Min Act: -0.0001

Data Index: 115083 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1077882 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9836. Min Act: -0.0001

Data Index: 882631 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.3234. Min Range: -1.3234

Max Act: 1.0046. Min Act: -0.0001

Data Index: 650223 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9839. Min Act: -0.0001

Data Index: 221642 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9517. Min Act: -0.0001

Data Index: 504595 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9458. Min Act: -0.0001

Data Index: 141143 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 1.3234. Min Range: -1.3234

Max Act: 0.9438. Min Act: -0.0000

Data Index: 244602 (C4 (Web Text))

Max Activating Token Index: 737