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

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

Neuron 3538 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: 1.0452. Min Range: -1.0452

Max Act: 1.0283. Min Act: -0.0002

Data Index: 263329 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.0452. Min Range: -1.0452

Max Act: 1.0452. Min Act: -0.0002

Data Index: 963478 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9866. Min Act: -0.0002

Data Index: 1038642 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9537. Min Act: -0.0002

Data Index: 1139848 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9392. Min Act: -0.0002

Data Index: 1203484 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8565. Min Act: -0.0002

Data Index: 977556 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9286. Min Act: -0.0002

Data Index: 292217 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8479. Min Act: -0.0002

Data Index: 1350122 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8347. Min Act: -0.0002

Data Index: 936596 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8424. Min Act: -0.0002

Data Index: 753314 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8570. Min Act: -0.0002

Data Index: 6231 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8875. Min Act: -0.0002

Data Index: 604508 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8702. Min Act: -0.0002

Data Index: 436306 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8246. Min Act: -0.0002

Data Index: 906112 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7877. Min Act: -0.0002

Data Index: 308415 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8586. Min Act: -0.0002

Data Index: 102016 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8389. Min Act: -0.0002

Data Index: 491933 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8894. Min Act: -0.0002

Data Index: 207360 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7999. Min Act: -0.0002

Data Index: 744237 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7764. Min Act: -0.0002

Data Index: 1355019 (C4 (Web Text))

Max Activating Token Index: 422