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

Dataset: The Pile

Neuron 774 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: 0.9271. Min Range: -0.9271

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1454287 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8770. Min Act: -0.0000

Data Index: 119491 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8390. Min Act: -0.0000

Data Index: 419682 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8206. Min Act: -0.0000

Data Index: 259603 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8189. Min Act: -0.0000

Data Index: 881252 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7807. Min Act: -0.0000

Data Index: 396240 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1602126 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1169737 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1737203 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7917. Min Act: -0.0000

Data Index: 399410 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1522997 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7336. Min Act: -0.0000

Data Index: 5300 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7188. Min Act: -0.0000

Data Index: 277755 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7357. Min Act: -0.0000

Data Index: 496722 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1038223 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7309. Min Act: -0.0000

Data Index: 78297 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1721528 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1313918 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7153. Min Act: -0.0000

Data Index: 281461 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1617805 (The Pile)

Max Activating Token Index: 860