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

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

Neuron 3408 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2650. Min Range: -3.2650

Max Act: 3.0922. Min Act: -0.0001

Data Index: 1271874 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 3.2650. Min Range: -3.2650

Max Act: 3.2650. Min Act: -0.0002

Data Index: 653959 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.8204. Min Act: -0.0001

Data Index: 1269359 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.8750. Min Act: -0.0001

Data Index: 1197734 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.8978. Min Act: -0.0001

Data Index: 500379 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.8727. Min Act: -0.0001

Data Index: 324278 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.8750. Min Act: -0.0001

Data Index: 44618 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.9141. Min Act: -0.0001

Data Index: 587597 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.5071. Min Act: -0.0001

Data Index: 855699 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.6910. Min Act: -0.0001

Data Index: 872322 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.7804. Min Act: -0.0001

Data Index: 889493 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.6924. Min Act: -0.0001

Data Index: 1043986 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.4814. Min Act: -0.0001

Data Index: 61628 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.7157. Min Act: -0.0001

Data Index: 798949 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.4351. Min Act: -0.0002

Data Index: 289555 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.4797. Min Act: -0.0001

Data Index: 442918 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.5572. Min Act: -0.0001

Data Index: 234311 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.6220. Min Act: -0.0001

Data Index: 229801 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.6655. Min Act: -0.0001

Data Index: 1043241 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 3.2650. Min Range: -3.2650

Max Act: 2.6117. Min Act: -0.0001

Data Index: 609631 (C4 (Web Text))

Max Activating Token Index: 879