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

Dataset: The Pile

Neuron 251 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: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0000

Data Index: 313832 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1785176 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1196. Min Act: -0.0000

Data Index: 325450 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1671030 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1077. Min Act: -0.0000

Data Index: 784940 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1069. Min Act: -0.0000

Data Index: 846239 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1106. Min Act: -0.0000

Data Index: 653632 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1093. Min Act: -0.0000

Data Index: 306060 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1040646 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1024. Min Act: -0.0000

Data Index: 343793 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0983. Min Act: -0.0000

Data Index: 735116 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1643443 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0994. Min Act: -0.0000

Data Index: 488858 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1084823 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1682057 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1198261 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0986. Min Act: -0.0000

Data Index: 792857 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1061100 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0961. Min Act: -0.0000

Data Index: 427040 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1380089 (The Pile)

Max Activating Token Index: 528