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

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

Neuron 3209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.1149. Min Act: -0.0001

Data Index: 1093303 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0912. Min Act: -0.0001

Data Index: 720388 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1000460 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.1240. Min Act: -0.0001

Data Index: 918084 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0157. Min Act: -0.0001

Data Index: 495017 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0613. Min Act: -0.0001

Data Index: 1341907 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0181. Min Act: -0.0001

Data Index: 237664 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9845. Min Act: -0.0001

Data Index: 121460 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1345608 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.8614. Min Act: -0.0001

Data Index: 941226 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9785. Min Act: -0.0001

Data Index: 481312 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9172. Min Act: -0.0001

Data Index: 1058758 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9443. Min Act: -0.0001

Data Index: 1190145 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1002617 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0256. Min Act: -0.0001

Data Index: 237937 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9581. Min Act: -0.0001

Data Index: 807889 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 1.1240. Min Range: -1.1240

Max Act: 1.0261. Min Act: -0.0001

Data Index: 739187 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1049458 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1037218 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.1240. Min Range: -1.1240

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1191338 (C4 (Web Text))

Max Activating Token Index: 1016