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

Dataset: The Pile

Neuron 3730 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: 0.2946. Min Range: -0.2946

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1336855 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1150574 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2498. Min Act: -0.0000

Data Index: 282211 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2383. Min Act: -0.0000

Data Index: 987469 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2428. Min Act: -0.0000

Data Index: 421109 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1446045 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2163. Min Act: -0.0000

Data Index: 131192 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2137. Min Act: -0.0000

Data Index: 249778 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2062. Min Act: -0.0000

Data Index: 475606 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1993. Min Act: -0.0000

Data Index: 338945 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1840. Min Act: -0.0000

Data Index: 750285 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1842. Min Act: -0.0000

Data Index: 682868 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1828. Min Act: -0.0000

Data Index: 888484 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1562. Min Act: -0.0000

Data Index: 689006 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1773. Min Act: -0.0000

Data Index: 298744 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1510171 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1989055 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1995733 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1490793 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1283039 (The Pile)

Max Activating Token Index: 178