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

Dataset: The Pile

Neuron 594 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5322. Min Act: -0.0000

Data Index: 69804 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1716206 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1670775 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3968. Min Act: 0.0000

Data Index: 939974 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3643. Min Act: -0.0000

Data Index: 388939 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3557. Min Act: -0.0000

Data Index: 436532 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3529. Min Act: 0.0000

Data Index: 1895359 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3543. Min Act: -0.0000

Data Index: 826328 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1088194 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1322452 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1807941 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3557. Min Act: -0.0000

Data Index: 932413 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1527157 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1418345 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1842703 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1952819 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1393492 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3386. Min Act: -0.0000

Data Index: 204778 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3279. Min Act: -0.0000

Data Index: 514623 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3063. Min Act: -0.0000

Data Index: 34368 (The Pile)

Max Activating Token Index: 118