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

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

Neuron 2503 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: 1.5156. Min Range: -1.5156

Max Act: 1.5156. Min Act: -0.0001

Data Index: 1074900 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2485. Min Act: -0.0001

Data Index: 84628 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2147. Min Act: -0.0001

Data Index: 635442 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1141. Min Act: -0.0001

Data Index: 1355449 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1427. Min Act: -0.0001

Data Index: 1313205 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.0788. Min Act: -0.0001

Data Index: 763493 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1265171 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.0083. Min Act: -0.0001

Data Index: 1186471 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8994. Min Act: -0.0001

Data Index: 893733 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9308. Min Act: -0.0001

Data Index: 933080 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8738. Min Act: -0.0001

Data Index: 480391 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9016. Min Act: -0.0001

Data Index: 666867 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9160. Min Act: -0.0001

Data Index: 1077136 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9206. Min Act: -0.0001

Data Index: 411990 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8977. Min Act: -0.0001

Data Index: 553248 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1042900 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1003512 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8765. Min Act: -0.0001

Data Index: 155338 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.9453. Min Act: -0.0001

Data Index: 205496 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.5156. Min Range: -1.5156

Max Act: 0.8157. Min Act: -0.0001

Data Index: 1038507 (C4 (Web Text))

Max Activating Token Index: 499