Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1473988 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1624784 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1825965 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1981599 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2200. Min Act: -0.0000

Data Index: 805333 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2195. Min Act: -0.0000

Data Index: 551910 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1022198 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2295. Min Act: -0.0000

Data Index: 895580 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1743827 (The Pile)

Max Activating Token Index: 720

Text #9

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1256793 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1541358 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2141. Min Act: -0.0000

Data Index: 444465 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2229. Min Act: -0.0000

Data Index: 967990 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1225162 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1389432 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1966. Min Act: -0.0000

Data Index: 140163 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1926997 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1526353 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1907368 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1778. Min Act: -0.0000

Data Index: 940323 (The Pile)

Max Activating Token Index: 711