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

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

Neuron 2139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4471. Min Act: 0.0001

Data Index: 1547329 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4087. Min Act: 0.0000

Data Index: 1490535 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1653586 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1461504 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1474091 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4015. Min Act: -0.0001

Data Index: 1544192 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1411028 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3719. Min Act: 0.0000

Data Index: 1522820 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3726. Min Act: 0.0000

Data Index: 1594485 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1545727 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1592943 (Python Code)

Max Activating Token Index: 904

Text #11

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1479465 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1613352 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1472391 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3591. Min Act: 0.0002

Data Index: 1639025 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3586. Min Act: 0.0001

Data Index: 1464659 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3811. Min Act: 0.0000

Data Index: 1398537 (Python Code)

Max Activating Token Index: 289

Text #17

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3428. Min Act: 0.0000

Data Index: 1492282 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1490277 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3490. Min Act: 0.0000

Data Index: 1451574 (Python Code)

Max Activating Token Index: 264