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

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

Neuron 897 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.6248. Min Act: -0.0000

Data Index: 196278 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.8377. Min Act: -0.0000

Data Index: 1244239 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.8392. Min Act: -0.0000

Data Index: 276049 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.6205. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.7450. Min Act: -0.0000

Data Index: 587195 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.6710. Min Act: -0.0000

Data Index: 665384 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.6005. Min Act: -0.0000

Data Index: 1227280 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.2816. Min Act: -0.0000

Data Index: 872658 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 7.8392. Min Range: -7.8392

Max Act: 7.0592. Min Act: -0.0000

Data Index: 538534 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.4066. Min Act: -0.0000

Data Index: 115856 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.2407. Min Act: -0.0000

Data Index: 1203119 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.4119. Min Act: -0.0000

Data Index: 187843 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.3424. Min Act: -0.0000

Data Index: 1219045 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.3240. Min Act: -0.0000

Data Index: 16615 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.2908. Min Act: -0.0000

Data Index: 933899 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.2454. Min Act: -0.0000

Data Index: 589322 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.2134. Min Act: -0.0000

Data Index: 142779 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 7.8392. Min Range: -7.8392

Max Act: 4.9601. Min Act: -0.0000

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 7.8392. Min Range: -7.8392

Max Act: 5.0896. Min Act: -0.0000

Data Index: 1317768 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 7.8392. Min Range: -7.8392

Max Act: 4.9783. Min Act: 0.0000

Data Index: 624684 (C4 (Web Text))

Max Activating Token Index: 500