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

Dataset: The Pile

Neuron 2433 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: 0.8054. Min Range: -0.8054

Max Act: 0.8054. Min Act: -0.0000

Data Index: 816386 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1358556 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1488206 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5132. Min Act: -0.0000

Data Index: 115698 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1876377 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5363. Min Act: -0.0000

Data Index: 336968 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1463314 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4793. Min Act: -0.0000

Data Index: 263979 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4879. Min Act: -0.0000

Data Index: 876416 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4668. Min Act: -0.0000

Data Index: 544584 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4740. Min Act: -0.0000

Data Index: 203982 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1114609 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1463483 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1984254 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1860522 (The Pile)

Max Activating Token Index: 902

Text #15

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4155. Min Act: -0.0000

Data Index: 946781 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1185910 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4193. Min Act: -0.0000

Data Index: 97055 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4300. Min Act: -0.0000

Data Index: 821077 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1496684 (The Pile)

Max Activating Token Index: 759