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

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

Neuron 3993 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: 0.8936. Min Range: -0.8936

Max Act: 0.8735. Min Act: -0.0002

Data Index: 590491 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8367. Min Act: -0.0002

Data Index: 635940 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7985. Min Act: -0.0002

Data Index: 1261733 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8936. Min Act: -0.0002

Data Index: 1047986 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8593. Min Act: -0.0002

Data Index: 914163 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8442. Min Act: -0.0002

Data Index: 234366 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8890. Min Act: -0.0002

Data Index: 617811 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8667. Min Act: -0.0002

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8829. Min Act: -0.0003

Data Index: 1012668 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8295. Min Act: -0.0002

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8140. Min Act: -0.0002

Data Index: 832392 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8419. Min Act: -0.0002

Data Index: 353625 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8182. Min Act: -0.0002

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7668. Min Act: -0.0002

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8433. Min Act: -0.0002

Data Index: 1039026 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8442. Min Act: -0.0002

Data Index: 424235 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7905. Min Act: -0.0002

Data Index: 92556 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8368. Min Act: -0.0002

Data Index: 1153012 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.7844. Min Act: -0.0002

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.8936. Min Range: -0.8936

Max Act: 0.8051. Min Act: -0.0002

Data Index: 432870 (C4 (Web Text))

Max Activating Token Index: 401