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

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

Neuron 481 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2551. Min Range: -2.2551

Max Act: 2.2551. Min Act: -0.0000

Data Index: 839679 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 2.2551. Min Range: -2.2551

Max Act: 2.1017. Min Act: -0.0000

Data Index: 377141 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.2551. Min Range: -2.2551

Max Act: 2.1449. Min Act: -0.0000

Data Index: 246872 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.2551. Min Range: -2.2551

Max Act: 2.0355. Min Act: -0.0000

Data Index: 27423 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 2.2551. Min Range: -2.2551

Max Act: 2.1024. Min Act: -0.0000

Data Index: 579630 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.8100. Min Act: -0.0000

Data Index: 752750 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.8293. Min Act: -0.0000

Data Index: 211029 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1154252 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.6934. Min Act: -0.0000

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.7478. Min Act: -0.0000

Data Index: 930244 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.8032. Min Act: -0.0000

Data Index: 371199 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.7006. Min Act: -0.0000

Data Index: 127884 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.7080. Min Act: -0.0000

Data Index: 908794 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.6488. Min Act: -0.0000

Data Index: 298758 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.6707. Min Act: -0.0000

Data Index: 98036 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.6338. Min Act: -0.0000

Data Index: 172597 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.3897. Min Act: -0.0000

Data Index: 371 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.5662. Min Act: -0.0000

Data Index: 959013 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.5770. Min Act: -0.0000

Data Index: 448022 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.2551. Min Range: -2.2551

Max Act: 1.5541. Min Act: -0.0000

Data Index: 254557 (C4 (Web Text))

Max Activating Token Index: 829