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

Dataset: The Pile

Neuron 898 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1796269 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.3001. Min Act: -0.0000

Data Index: 601238 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2766. Min Act: -0.0000

Data Index: 887283 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1412696 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1489195 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1911032 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1677238 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2710. Min Act: -0.0000

Data Index: 798723 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1175482 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1194778 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1208 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2582. Min Act: -0.0000

Data Index: 950414 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1890067 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2577. Min Act: -0.0000

Data Index: 45959 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1964788 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2521. Min Act: -0.0000

Data Index: 62473 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1939772 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1612657 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1150662 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2439. Min Act: -0.0000

Data Index: 280507 (The Pile)

Max Activating Token Index: 720