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

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

Neuron 248 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8255. Min Range: -2.8255

Max Act: 2.8255. Min Act: -0.0000

Data Index: 1188203 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 2.8255. Min Range: -2.8255

Max Act: 2.2246. Min Act: -0.0000

Data Index: 899241 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 2.8255. Min Range: -2.8255

Max Act: 2.2644. Min Act: -0.0000

Data Index: 449075 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 2.8255. Min Range: -2.8255

Max Act: 2.1172. Min Act: -0.0000

Data Index: 88664 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.9886. Min Act: -0.0000

Data Index: 13884 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 2.8255. Min Range: -2.8255

Max Act: 2.1187. Min Act: -0.0000

Data Index: 568365 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1324754 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.8699. Min Act: -0.0000

Data Index: 1199455 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1225493 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.9912. Min Act: -0.0000

Data Index: 782144 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.8728. Min Act: 0.0000

Data Index: 1127365 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.8646. Min Act: -0.0000

Data Index: 530104 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.8494. Min Act: -0.0000

Data Index: 1501103 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.6419. Min Act: -0.0000

Data Index: 459144 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.7461. Min Act: -0.0000

Data Index: 588911 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.8031. Min Act: -0.0000

Data Index: 551440 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1478369 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.6670. Min Act: -0.0000

Data Index: 414524 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.7461. Min Act: -0.0000

Data Index: 1279274 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.8255. Min Range: -2.8255

Max Act: 1.6294. Min Act: -0.0000

Data Index: 79723 (C4 (Web Text))

Max Activating Token Index: 292