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

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

Neuron 519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1717. Min Range: -1.1717

Max Act: 1.1717. Min Act: -0.0000

Data Index: 770420 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.1717. Min Range: -1.1717

Max Act: 1.0324. Min Act: -0.0000

Data Index: 423647 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.9040. Min Act: -0.0000

Data Index: 819155 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1628607 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.8126. Min Act: -0.0000

Data Index: 353700 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.8278. Min Act: -0.0000

Data Index: 981174 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1139914 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.6690. Min Act: -0.0000

Data Index: 316301 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1208012 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7685. Min Act: -0.0000

Data Index: 284422 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7754. Min Act: -0.0000

Data Index: 835365 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7583. Min Act: -0.0000

Data Index: 671091 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7723. Min Act: -0.0000

Data Index: 606777 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7465. Min Act: -0.0000

Data Index: 462287 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7537. Min Act: -0.0000

Data Index: 555705 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1209199 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1080933 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7510. Min Act: -0.0000

Data Index: 557076 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1192232 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 1.1717. Min Range: -1.1717

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1111783 (C4 (Web Text))

Max Activating Token Index: 308