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

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

Neuron 4760 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1366. Min Act: 0.0000

Data Index: 1270881 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1209751 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0000

Data Index: 138830 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1174. Min Act: -0.0000

Data Index: 243903 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1225. Min Act: -0.0000

Data Index: 426863 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1173. Min Act: -0.0000

Data Index: 333004 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1143. Min Act: -0.0000

Data Index: 569851 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1181. Min Act: -0.0000

Data Index: 557138 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1060949 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1204. Min Act: -0.0000

Data Index: 755734 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1171. Min Act: -0.0000

Data Index: 532081 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1117. Min Act: -0.0000

Data Index: 575931 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1152. Min Act: -0.0000

Data Index: 920767 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1140. Min Act: -0.0000

Data Index: 525576 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1145. Min Act: -0.0000

Data Index: 421101 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1180. Min Act: -0.0000

Data Index: 958573 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1127. Min Act: -0.0000

Data Index: 952516 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1070. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1090. Min Act: -0.0000

Data Index: 3756 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1288206 (C4 (Web Text))

Max Activating Token Index: 773