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

Dataset: The Pile

Neuron 55 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: 0.1595. Min Range: -0.1595

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1776547 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1670431 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1544. Min Act: -0.0000

Data Index: 207592 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1904678 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1310174 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1458. Min Act: -0.0000

Data Index: 499850 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1500. Min Act: -0.0000

Data Index: 414546 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1377. Min Act: -0.0000

Data Index: 992907 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1327. Min Act: -0.0000

Data Index: 951744 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1749573 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1829919 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1292. Min Act: -0.0000

Data Index: 992230 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1194. Min Act: -0.0000

Data Index: 477521 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1295. Min Act: -0.0000

Data Index: 472759 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1261. Min Act: -0.0000

Data Index: 535843 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1271. Min Act: -0.0000

Data Index: 693006 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1815230 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1333. Min Act: -0.0000

Data Index: 804394 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1195. Min Act: -0.0000

Data Index: 185825 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1819209 (The Pile)

Max Activating Token Index: 101