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

Dataset: The Pile

Neuron 1740 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1106914 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6310. Min Act: -0.0000

Data Index: 40459 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1307275 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1651234 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1849475 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5450. Min Act: -0.0000

Data Index: 972394 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1319540 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1645447 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5219. Min Act: -0.0000

Data Index: 930676 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5605. Min Act: -0.0000

Data Index: 515999 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1978356 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5172. Min Act: -0.0000

Data Index: 427533 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1992978 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1911579 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4939. Min Act: -0.0000

Data Index: 54654 (The Pile)

Max Activating Token Index: 85

Text #15

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5066. Min Act: -0.0000

Data Index: 499568 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1057235 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1267008 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1410769 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1437038 (The Pile)

Max Activating Token Index: 590