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

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

Neuron 5467 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0093. Min Range: -6.0093

Max Act: 6.0093. Min Act: -0.0000

Data Index: 657908 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 6.0093. Min Range: -6.0093

Max Act: 5.6942. Min Act: -0.0000

Data Index: 844739 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.8973. Min Act: -0.0000

Data Index: 606177 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.7286. Min Act: -0.0000

Data Index: 1340465 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.6636. Min Act: -0.0000

Data Index: 886777 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.5792. Min Act: -0.0000

Data Index: 1332432 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.5126. Min Act: -0.0000

Data Index: 870800 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.9554. Min Act: -0.0000

Data Index: 983686 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.3833. Min Act: -0.0000

Data Index: 137758 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.4252. Min Act: -0.0000

Data Index: 973582 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.3569. Min Act: -0.0000

Data Index: 414981 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 6.0093. Min Range: -6.0093

Max Act: 3.9603. Min Act: -0.0000

Data Index: 680565 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.2655. Min Act: -0.0000

Data Index: 260308 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.1011. Min Act: -0.0000

Data Index: 610910 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 6.0093. Min Range: -6.0093

Max Act: 3.9252. Min Act: -0.0000

Data Index: 205400 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.3927. Min Act: -0.0000

Data Index: 2015 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.2187. Min Act: -0.0000

Data Index: 9063 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 6.0093. Min Range: -6.0093

Max Act: 3.8521. Min Act: -0.0000

Data Index: 367576 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 6.0093. Min Range: -6.0093

Max Act: 3.8310. Min Act: -0.0000

Data Index: 1336344 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 6.0093. Min Range: -6.0093

Max Act: 4.0144. Min Act: -0.0000

Data Index: 170390 (C4 (Web Text))

Max Activating Token Index: 83