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

Dataset: The Pile

Neuron 994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1233345 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2909. Min Act: -0.0000

Data Index: 480942 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1796071 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1962344 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1501332 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1325169 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1170540 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2442. Min Act: -0.0000

Data Index: 973414 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2608. Min Act: -0.0000

Data Index: 805119 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1353075 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1461335 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1986065 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2218. Min Act: -0.0000

Data Index: 268207 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2291. Min Act: -0.0000

Data Index: 859568 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1664530 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1908616 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.1977. Min Act: -0.0000

Data Index: 216917 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1343228 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2133. Min Act: -0.0000

Data Index: 131458 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1318287 (The Pile)

Max Activating Token Index: 658