Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4083 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7961. Min Act: -0.0000

Data Index: 307920 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.8231. Min Act: -0.0000

Data Index: 957908 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7172. Min Act: -0.0000

Data Index: 1042971 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7212. Min Act: -0.0000

Data Index: 951189 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6852. Min Act: -0.0000

Data Index: 1221962 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6273. Min Act: -0.0000

Data Index: 669158 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6248. Min Act: -0.0000

Data Index: 380756 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6156. Min Act: -0.0000

Data Index: 826587 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6025. Min Act: -0.0000

Data Index: 493894 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5164. Min Act: -0.0000

Data Index: 46972 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1275047 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6021. Min Act: -0.0000

Data Index: 156163 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1000263 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5951. Min Act: -0.0000

Data Index: 1266940 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5018. Min Act: -0.0000

Data Index: 494400 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5906. Min Act: -0.0000

Data Index: 525261 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5044. Min Act: -0.0000

Data Index: 333797 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5872. Min Act: -0.0000

Data Index: 108443 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5829. Min Act: -0.0000

Data Index: 922194 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5507. Min Act: -0.0000

Data Index: 708491 (C4 (Web Text))

Max Activating Token Index: 830