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

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

Neuron 2859 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1361118 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0000

Data Index: 416247 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7000. Min Act: -0.0000

Data Index: 680447 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7260. Min Act: -0.0000

Data Index: 421389 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6942. Min Act: -0.0000

Data Index: 556577 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1601762 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1450974 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1431641 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1227582 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1415983 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5721. Min Act: -0.0000

Data Index: 513585 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5442. Min Act: -0.0000

Data Index: 42348 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5610. Min Act: -0.0000

Data Index: 988204 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5437. Min Act: -0.0000

Data Index: 628040 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1482878 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5543. Min Act: -0.0000

Data Index: 484881 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5377. Min Act: -0.0000

Data Index: 348658 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5355. Min Act: -0.0000

Data Index: 534184 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5305. Min Act: -0.0000

Data Index: 428828 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1155723 (C4 (Web Text))

Max Activating Token Index: 979