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

Dataset: The Pile

Neuron 514 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: 1.2317. Min Range: -1.2317

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1607499 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.1316. Min Act: -0.0000

Data Index: 376144 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1252596 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0092. Min Act: -0.0000

Data Index: 263035 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1020438 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1149192 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.2317. Min Range: -1.2317

Max Act: 1.0115. Min Act: -0.0000

Data Index: 713193 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1139006 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8301. Min Act: -0.0000

Data Index: 996689 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1605201 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8460. Min Act: -0.0000

Data Index: 155581 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8450. Min Act: -0.0000

Data Index: 64769 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1221623 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1454489 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8086. Min Act: -0.0000

Data Index: 703747 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8267. Min Act: -0.0000

Data Index: 767136 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8014. Min Act: -0.0000

Data Index: 284618 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.7397. Min Act: -0.0000

Data Index: 974989 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1629524 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.2317. Min Range: -1.2317

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1737883 (The Pile)

Max Activating Token Index: 400