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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2023 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5945. Min Act: -0.0001

Data Index: 1136080 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4763. Min Act: -0.0001

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5176. Min Act: -0.0001

Data Index: 621991 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5667. Min Act: -0.0001

Data Index: 1147726 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5412. Min Act: -0.0001

Data Index: 604520 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5041. Min Act: -0.0001

Data Index: 1207794 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5093. Min Act: -0.0001

Data Index: 700115 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5492. Min Act: -0.0001

Data Index: 907752 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4642. Min Act: -0.0001

Data Index: 1267055 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.5160. Min Act: -0.0001

Data Index: 891612 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4325. Min Act: -0.0001

Data Index: 860578 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4621. Min Act: -0.0001

Data Index: 1070491 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.3724. Min Act: -0.0001

Data Index: 1205111 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.3376. Min Act: -0.0001

Data Index: 56850 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4061. Min Act: -0.0001

Data Index: 185934 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4327. Min Act: -0.0001

Data Index: 501226 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.3944. Min Act: -0.0001

Data Index: 252172 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.3232. Min Act: -0.0001

Data Index: 831592 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4212. Min Act: -0.0001

Data Index: 129066 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.5945. Min Range: -1.5945

Max Act: 1.4315. Min Act: -0.0001

Data Index: 1051957 (C4 (Web Text))

Max Activating Token Index: 583