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

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

Neuron 5569 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1311405 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.5056. Min Act: -0.0000

Data Index: 101068 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1012965 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4763. Min Act: -0.0000

Data Index: 284820 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1110721 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4894. Min Act: -0.0000

Data Index: 627752 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4706. Min Act: -0.0000

Data Index: 777210 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4674. Min Act: -0.0000

Data Index: 250930 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4473. Min Act: -0.0000

Data Index: 456683 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4476. Min Act: -0.0000

Data Index: 951544 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4554. Min Act: -0.0000

Data Index: 289581 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4548. Min Act: -0.0000

Data Index: 782658 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4217. Min Act: -0.0000

Data Index: 738353 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1311255 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.3899. Min Act: -0.0000

Data Index: 17537 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4195. Min Act: -0.0000

Data Index: 850244 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4311. Min Act: -0.0000

Data Index: 420955 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4161. Min Act: -0.0000

Data Index: 438753 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.3980. Min Act: -0.0000

Data Index: 864988 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.5241. Min Range: -0.5241

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1168680 (C4 (Web Text))

Max Activating Token Index: 835