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

Dataset: The Pile

Neuron 4069 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: 0.4869. Min Range: -0.4869

Max Act: 0.4869. Min Act: -0.0000

Data Index: 190185 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1831373 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4166. Min Act: -0.0000

Data Index: 315896 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1012509 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1194003 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3906. Min Act: -0.0000

Data Index: 915616 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1925554 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1164575 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1587169 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1195761 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3505. Min Act: -0.0000

Data Index: 652990 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1003245 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1108725 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3414. Min Act: -0.0000

Data Index: 715044 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3361. Min Act: -0.0000

Data Index: 954734 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1030349 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2961. Min Act: -0.0000

Data Index: 707745 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1644000 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1802980 (The Pile)

Max Activating Token Index: 823

Text #19

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1381713 (The Pile)

Max Activating Token Index: 20