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

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

Neuron 1689 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7599. Min Act: -0.0001

Data Index: 1149086 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7110. Min Act: -0.0001

Data Index: 1189390 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7169. Min Act: -0.0001

Data Index: 371135 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7578. Min Act: -0.0000

Data Index: 393819 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7054. Min Act: -0.0001

Data Index: 127509 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6120. Min Act: -0.0001

Data Index: 209598 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6859. Min Act: -0.0001

Data Index: 1116958 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6954. Min Act: -0.0001

Data Index: 586553 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7363. Min Act: -0.0001

Data Index: 507196 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7189. Min Act: -0.0000

Data Index: 1144349 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7051. Min Act: -0.0001

Data Index: 98060 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1035915 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6367. Min Act: -0.0000

Data Index: 789672 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.5476. Min Act: -0.0001

Data Index: 647670 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4435. Min Act: -0.0000

Data Index: 665574 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.5588. Min Act: -0.0001

Data Index: 738044 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4921. Min Act: -0.0001

Data Index: 1308405 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.5844. Min Act: -0.0000

Data Index: 646019 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1050385 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6157. Min Act: -0.0001

Data Index: 80857 (C4 (Web Text))

Max Activating Token Index: 829