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

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

Neuron 4817 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4490. Min Act: -0.0002

Data Index: 1032374 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4522. Min Act: -0.0002

Data Index: 748401 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4287. Min Act: -0.0002

Data Index: 1303332 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4220. Min Act: -0.0002

Data Index: 315927 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4386. Min Act: -0.0002

Data Index: 578994 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4151. Min Act: -0.0002

Data Index: 755251 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3908. Min Act: -0.0002

Data Index: 775046 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3694. Min Act: -0.0002

Data Index: 1287847 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3757. Min Act: -0.0002

Data Index: 1211468 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3644. Min Act: -0.0002

Data Index: 1357635 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3852. Min Act: -0.0002

Data Index: 1015423 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3929. Min Act: -0.0002

Data Index: 840992 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3214. Min Act: -0.0002

Data Index: 484412 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3885. Min Act: -0.0002

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3398. Min Act: -0.0002

Data Index: 397156 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3399. Min Act: -0.0002

Data Index: 427156 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3490. Min Act: -0.0002

Data Index: 1085302 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3230. Min Act: -0.0002

Data Index: 59830 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3269. Min Act: -0.0002

Data Index: 896724 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3336. Min Act: -0.0002

Data Index: 494790 (C4 (Web Text))

Max Activating Token Index: 288