Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1158 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1515599 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1413124 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1950927 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2430. Min Act: -0.0000

Data Index: 336283 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1265709 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1080132 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2763. Min Act: -0.0000

Data Index: 392280 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1956630 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1948587 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1979867 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2843. Min Act: -0.0000

Data Index: 600288 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1869018 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1974533 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2196. Min Act: -0.0000

Data Index: 514725 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2315. Min Act: -0.0000

Data Index: 95449 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2457. Min Act: -0.0000

Data Index: 790353 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2399. Min Act: -0.0000

Data Index: 74409 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2294. Min Act: -0.0000

Data Index: 303966 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2611. Min Act: -0.0000

Data Index: 413880 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1057858 (The Pile)

Max Activating Token Index: 310