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

Dataset: The Pile

Neuron 2270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.7086. Min Act: -0.0000

Data Index: 649536 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.2107. Min Act: -0.0000

Data Index: 846120 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.1374. Min Act: -0.0000

Data Index: 1108746 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1227419 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1702608 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1737292 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1099910 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0969. Min Act: -0.0000

Data Index: 467719 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1307852 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0607. Min Act: -0.0000

Data Index: 359585 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1947810 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1093569 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0491. Min Act: -0.0000

Data Index: 163349 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1555346 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.7086. Min Range: -1.7086

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1858713 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1599218 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0749. Min Act: -0.0000

Data Index: 899626 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0449. Min Act: -0.0000

Data Index: 871651 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1126635 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 1.7086. Min Range: -1.7086

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1233743 (The Pile)

Max Activating Token Index: 707