Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.3004. Min Act: -0.0001

Data Index: 405595 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.4399. Min Act: -0.0001

Data Index: 740900 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.2498. Min Act: -0.0001

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.3137. Min Act: -0.0001

Data Index: 205706 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.3095. Min Act: -0.0001

Data Index: 245504 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.3039. Min Act: -0.0001

Data Index: 77647 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.2513. Min Act: -0.0001

Data Index: 1102426 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.1421. Min Act: -0.0001

Data Index: 1049892 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0804. Min Act: -0.0001

Data Index: 1066024 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.1678. Min Act: -0.0001

Data Index: 886414 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.1212. Min Act: -0.0001

Data Index: 705469 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0526. Min Act: -0.0001

Data Index: 223920 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0649. Min Act: -0.0001

Data Index: 313889 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0687. Min Act: -0.0001

Data Index: 1086293 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0953. Min Act: -0.0001

Data Index: 410288 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0594. Min Act: -0.0001

Data Index: 690716 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0295. Min Act: -0.0001

Data Index: 754952 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0838. Min Act: -0.0001

Data Index: 1087832 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0757. Min Act: -0.0001

Data Index: 959918 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.4399. Min Range: -1.4399

Max Act: 1.0629. Min Act: -0.0001

Data Index: 386249 (C4 (Web Text))

Max Activating Token Index: 570