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

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

Neuron 509 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: 1.3156. Min Range: -1.3156

Max Act: 1.3156. Min Act: -0.0001

Data Index: 345474 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2116. Min Act: -0.0001

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.1593. Min Act: -0.0001

Data Index: 1175852 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.1163. Min Act: -0.0001

Data Index: 137483 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2571. Min Act: -0.0001

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.1367. Min Act: -0.0001

Data Index: 135160 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0924. Min Act: -0.0001

Data Index: 220526 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0759. Min Act: -0.0001

Data Index: 1016612 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1125579 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0496. Min Act: -0.0001

Data Index: 452784 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0350. Min Act: -0.0001

Data Index: 414470 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0615. Min Act: -0.0001

Data Index: 99033 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0238. Min Act: -0.0001

Data Index: 860662 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0441. Min Act: -0.0001

Data Index: 956526 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0139. Min Act: -0.0001

Data Index: 932844 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9668. Min Act: -0.0001

Data Index: 712810 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.0391. Min Act: -0.0001

Data Index: 966459 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.3156. Min Range: -1.3156

Max Act: 1.1293. Min Act: -0.0001

Data Index: 256887 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9986. Min Act: -0.0001

Data Index: 663764 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.3156. Min Range: -1.3156

Max Act: 0.9953. Min Act: -0.0001

Data Index: 618042 (C4 (Web Text))

Max Activating Token Index: 574