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

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

Neuron 1579 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: 5.2138. Min Range: -5.2138

Max Act: 5.2138. Min Act: -0.0000

Data Index: 582669 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.2138. Min Range: -5.2138

Max Act: 4.4528. Min Act: -0.0001

Data Index: 181847 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 5.2138. Min Range: -5.2138

Max Act: 4.4297. Min Act: -0.0001

Data Index: 432140 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 5.2138. Min Range: -5.2138

Max Act: 4.0417. Min Act: -0.0001

Data Index: 189907 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 5.2138. Min Range: -5.2138

Max Act: 4.1800. Min Act: -0.0001

Data Index: 616354 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.8256. Min Act: -0.0000

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.7206. Min Act: -0.0001

Data Index: 171704 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.7756. Min Act: -0.0001

Data Index: 861670 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.6478. Min Act: -0.0001

Data Index: 159060 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.2778. Min Act: -0.0001

Data Index: 595562 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.2451. Min Act: -0.0001

Data Index: 607304 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.6538. Min Act: -0.0001

Data Index: 1314701 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.4801. Min Act: -0.0000

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.6075. Min Act: -0.0000

Data Index: 107347 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.3066. Min Act: -0.0001

Data Index: 679009 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.6562. Min Act: -0.0001

Data Index: 206036 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.3730. Min Act: -0.0001

Data Index: 177865 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.4544. Min Act: -0.0001

Data Index: 843594 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.1610. Min Act: -0.0001

Data Index: 69779 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 5.2138. Min Range: -5.2138

Max Act: 3.2638. Min Act: -0.0001

Data Index: 1277708 (C4 (Web Text))

Max Activating Token Index: 427