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

Dataset: The Pile

Neuron 4126 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: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1107186 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1789. Min Act: -0.0000

Data Index: 271744 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1155401 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1342. Min Act: -0.0000

Data Index: 727349 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1351486 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1200. Min Act: -0.0000

Data Index: 123144 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1184552 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1307. Min Act: -0.0000

Data Index: 392889 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1297981 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1362. Min Act: -0.0000

Data Index: 292865 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1404345 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1371722 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1359. Min Act: -0.0000

Data Index: 528225 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1126636 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1282. Min Act: -0.0000

Data Index: 83449 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1072. Min Act: -0.0000

Data Index: 539550 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1891175 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1245782 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1256. Min Act: -0.0000

Data Index: 144584 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1255. Min Act: -0.0000

Data Index: 929458 (The Pile)

Max Activating Token Index: 19