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

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

Neuron 2892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.2647. Min Act: -0.0001

Data Index: 1295089 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.3002. Min Act: -0.0001

Data Index: 671177 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1710. Min Act: -0.0001

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.1740. Min Act: -0.0001

Data Index: 366527 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0495. Min Act: -0.0001

Data Index: 837662 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0445. Min Act: -0.0001

Data Index: 214296 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0835. Min Act: -0.0001

Data Index: 1243249 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1350895 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9838. Min Act: -0.0001

Data Index: 1352492 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0031. Min Act: -0.0001

Data Index: 1221658 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0035. Min Act: -0.0001

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0167. Min Act: -0.0001

Data Index: 536395 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9254. Min Act: -0.0001

Data Index: 1142573 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1306077 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9189. Min Act: -0.0001

Data Index: 1265109 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1716 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9824. Min Act: -0.0001

Data Index: 728062 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 1.3002. Min Range: -1.3002

Max Act: 1.0072. Min Act: -0.0001

Data Index: 164542 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.9631. Min Act: -0.0001

Data Index: 1070414 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.3002. Min Range: -1.3002

Max Act: 0.8911. Min Act: -0.0001

Data Index: 596510 (C4 (Web Text))

Max Activating Token Index: 117