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

Dataset: The Pile

Neuron 3936 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: 0.1947. Min Range: -0.1947

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1353935 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1728. Min Act: -0.0000

Data Index: 799527 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1587. Min Act: -0.0000

Data Index: 702868 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1415753 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1899725 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1749. Min Act: -0.0000

Data Index: 696685 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1881507 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1731120 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1489. Min Act: -0.0000

Data Index: 472326 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1472. Min Act: -0.0000

Data Index: 398512 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1827540 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1580. Min Act: -0.0000

Data Index: 161931 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1563. Min Act: -0.0000

Data Index: 987680 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1854001 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1593. Min Act: -0.0000

Data Index: 616232 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1508969 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1680948 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1150482 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1786823 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1630. Min Act: -0.0000

Data Index: 691257 (The Pile)

Max Activating Token Index: 550