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

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

Neuron 4062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7224. Min Act: -0.0000

Data Index: 125348 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1616731 (Python Code)

Max Activating Token Index: 970

Text #2

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4997. Min Act: -0.0000

Data Index: 195301 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1535490 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4245. Min Act: -0.0000

Data Index: 443268 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1409492 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4349. Min Act: -0.0000

Data Index: 32378 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3941. Min Act: -0.0000

Data Index: 378985 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1094375 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4174. Min Act: -0.0000

Data Index: 367837 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1101079 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3635. Min Act: -0.0000

Data Index: 125796 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3706. Min Act: -0.0000

Data Index: 700491 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4093. Min Act: -0.0000

Data Index: 891325 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1378894 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1503063 (Python Code)

Max Activating Token Index: 936

Text #16

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1427700 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1381449 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1159030 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.3814. Min Act: -0.0000

Data Index: 287813 (C4 (Web Text))

Max Activating Token Index: 507