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

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

Neuron 4556 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2060. Min Range: -4.2060

Max Act: 4.2060. Min Act: 0.0000

Data Index: 1266399 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 4.2060. Min Range: -4.2060

Max Act: 4.1483. Min Act: -0.0000

Data Index: 591204 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.9349. Min Act: -0.0000

Data Index: 779702 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.7669. Min Act: -0.0000

Data Index: 985810 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.6185. Min Act: -0.0000

Data Index: 1220535 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.3541. Min Act: -0.0000

Data Index: 171078 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.2764. Min Act: -0.0000

Data Index: 313365 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1182730 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.0064. Min Act: -0.0000

Data Index: 770913 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 4.2060. Min Range: -4.2060

Max Act: 3.0034. Min Act: -0.0000

Data Index: 273567 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.9585. Min Act: -0.0000

Data Index: 532690 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.9402. Min Act: -0.0000

Data Index: 359248 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.7773. Min Act: -0.0000

Data Index: 1107734 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.7644. Min Act: -0.0000

Data Index: 13751 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.8675. Min Act: -0.0000

Data Index: 1082594 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.8008. Min Act: -0.0000

Data Index: 919827 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1281805 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.8394. Min Act: -0.0000

Data Index: 992603 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.6765. Min Act: -0.0000

Data Index: 1278942 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 4.2060. Min Range: -4.2060

Max Act: 2.7687. Min Act: -0.0000

Data Index: 632832 (C4 (Web Text))

Max Activating Token Index: 839