Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.3172. Min Act: -0.0001

Data Index: 845409 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.2931. Min Act: -0.0001

Data Index: 566347 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.1912. Min Act: -0.0001

Data Index: 250453 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.1719. Min Act: -0.0001

Data Index: 763266 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.1391. Min Act: -0.0001

Data Index: 828903 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.0743. Min Act: -0.0001

Data Index: 1065423 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.0753. Min Act: -0.0001

Data Index: 755068 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.1393. Min Act: -0.0001

Data Index: 1333349 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.0765. Min Act: -0.0001

Data Index: 844975 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.0462. Min Act: -0.0001

Data Index: 16007 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9809. Min Act: -0.0001

Data Index: 1208186 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9061. Min Act: -0.0001

Data Index: 369627 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9556. Min Act: -0.0001

Data Index: 629806 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9548. Min Act: -0.0001

Data Index: 218752 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.7803. Min Act: -0.0001

Data Index: 919353 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.3172. Min Range: -1.3172

Max Act: 1.0009. Min Act: -0.0001

Data Index: 856864 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.8777. Min Act: -0.0001

Data Index: 73533 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9614. Min Act: -0.0001

Data Index: 1173366 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9177. Min Act: -0.0001

Data Index: 1295590 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.3172. Min Range: -1.3172

Max Act: 0.9368. Min Act: -0.0001

Data Index: 346639 (C4 (Web Text))

Max Activating Token Index: 199