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

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

Neuron 5812 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6659. Min Act: -0.0000

Data Index: 711473 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1252910 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1405231 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5749. Min Act: -0.0000

Data Index: 121528 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1055659 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5827. Min Act: -0.0000

Data Index: 300493 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5659. Min Act: -0.0000

Data Index: 81826 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1393486 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4959. Min Act: -0.0000

Data Index: 251997 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4855. Min Act: -0.0000

Data Index: 353696 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1285316 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4524. Min Act: -0.0000

Data Index: 546384 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1653203 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4326. Min Act: -0.0000

Data Index: 301055 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4176. Min Act: -0.0000

Data Index: 662041 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1067873 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4328. Min Act: -0.0000

Data Index: 68469 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1283989 (C4 (Web Text))

Max Activating Token Index: 629