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

Dataset: The Pile

Neuron 4458 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: 4.0870. Min Range: -4.0870

Max Act: 4.0870. Min Act: -0.0000

Data Index: 215094 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.9159. Min Act: -0.0000

Data Index: 157725 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.9434. Min Act: -0.0000

Data Index: 571115 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.6245. Min Act: -0.0000

Data Index: 1409905 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5450. Min Act: -0.0000

Data Index: 1115142 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.2460. Min Act: -0.0000

Data Index: 1767580 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.3998. Min Act: -0.0000

Data Index: 1184389 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.4345. Min Act: -0.0000

Data Index: 55422 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.3320. Min Act: -0.0000

Data Index: 803482 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5307. Min Act: -0.0000

Data Index: 313011 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5256. Min Act: -0.0000

Data Index: 1147935 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.3641. Min Act: -0.0000

Data Index: 1798924 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.3432. Min Act: -0.0000

Data Index: 76532 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.1236. Min Act: -0.0000

Data Index: 1980921 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5751. Min Act: -0.0000

Data Index: 1683386 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.4082. Min Act: -0.0000

Data Index: 461652 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5827. Min Act: -0.0000

Data Index: 1168833 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.4801. Min Act: -0.0000

Data Index: 750344 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.5098. Min Act: -0.0000

Data Index: 815281 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 4.0870. Min Range: -4.0870

Max Act: 3.3420. Min Act: -0.0000

Data Index: 1295389 (The Pile)

Max Activating Token Index: 722