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

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

Neuron 1267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.1354. Min Act: -0.0000

Data Index: 904541 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.1713. Min Act: -0.0000

Data Index: 399014 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1113988 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.0170. Min Act: -0.0000

Data Index: 299563 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.0744. Min Act: -0.0000

Data Index: 377168 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.0137. Min Act: -0.0000

Data Index: 990188 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.9573. Min Act: -0.0000

Data Index: 583543 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8929. Min Act: -0.0000

Data Index: 56044 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1184332 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8819. Min Act: -0.0000

Data Index: 267527 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8404. Min Act: -0.0000

Data Index: 198633 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1231033 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8144. Min Act: -0.0000

Data Index: 693919 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8215. Min Act: -0.0000

Data Index: 292631 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8954. Min Act: -0.0000

Data Index: 199251 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7708. Min Act: -0.0000

Data Index: 650939 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1017060 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8484. Min Act: -0.0000

Data Index: 827728 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7956. Min Act: -0.0000

Data Index: 833588 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7035. Min Act: -0.0000

Data Index: 447771 (C4 (Web Text))

Max Activating Token Index: 272