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

Dataset: The Pile

Neuron 3055 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1765. Min Act: -0.0000

Data Index: 237003 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1714. Min Act: -0.0000

Data Index: 872600 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1731. Min Act: -0.0000

Data Index: 328266 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1521745 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1273183 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1456332 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1354620 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1508. Min Act: -0.0000

Data Index: 596203 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1620994 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1007410 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1433. Min Act: -0.0000

Data Index: 395134 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1675902 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1141223 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1503. Min Act: -0.0000

Data Index: 247058 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1557. Min Act: -0.0000

Data Index: 997637 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1009814 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1113157 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1169880 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1322. Min Act: -0.0000

Data Index: 7311 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1452. Min Act: -0.0000

Data Index: 50314 (The Pile)

Max Activating Token Index: 74