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

Dataset: The Pile

Neuron 2107 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: 0.6904. Min Range: -0.6904

Max Act: 0.6904. Min Act: -0.0000

Data Index: 823291 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1147155 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1338747 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1822702 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1379884 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1334478 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5559. Min Act: -0.0000

Data Index: 18983 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.6676. Min Act: -0.0000

Data Index: 73331 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1549143 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5488. Min Act: -0.0000

Data Index: 26479 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4156. Min Act: -0.0000

Data Index: 456695 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1261549 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1878045 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1400174 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5257. Min Act: -0.0000

Data Index: 225136 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1062380 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1015285 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1343243 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1569712 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4262. Min Act: -0.0000

Data Index: 68083 (The Pile)

Max Activating Token Index: 136