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

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

Neuron 4245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6849. Min Act: -0.0001

Data Index: 346870 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4079. Min Act: -0.0001

Data Index: 302805 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4260. Min Act: -0.0001

Data Index: 417470 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1277578 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3657. Min Act: -0.0001

Data Index: 713587 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3892. Min Act: -0.0001

Data Index: 931642 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3653. Min Act: -0.0001

Data Index: 131598 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1105372 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4056. Min Act: -0.0001

Data Index: 116926 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3364. Min Act: -0.0001

Data Index: 859348 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3507. Min Act: -0.0001

Data Index: 986503 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1034228 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3448. Min Act: -0.0001

Data Index: 964363 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3495. Min Act: -0.0001

Data Index: 137793 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3190. Min Act: -0.0001

Data Index: 910641 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1290258 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3370. Min Act: -0.0001

Data Index: 313003 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1078449 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3386. Min Act: -0.0001

Data Index: 595814 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.3436. Min Act: -0.0001

Data Index: 597226 (C4 (Web Text))

Max Activating Token Index: 911