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

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

Neuron 3872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.0322. Min Range: -5.0322

Max Act: 5.0322. Min Act: -0.0000

Data Index: 1139292 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.6927. Min Act: -0.0000

Data Index: 131311 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.5216. Min Act: -0.0000

Data Index: 49538 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.5007. Min Act: -0.0000

Data Index: 327269 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4766. Min Act: -0.0000

Data Index: 1040362 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4788. Min Act: -0.0000

Data Index: 788336 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4956. Min Act: -0.0000

Data Index: 400191 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.1377. Min Act: -0.0000

Data Index: 408000 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.9648. Min Act: -0.0000

Data Index: 325533 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.6617. Min Act: -0.0000

Data Index: 31918 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.1335. Min Act: -0.0000

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.2334. Min Act: -0.0000

Data Index: 1167095 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.1399. Min Act: -0.0000

Data Index: 679641 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.1126. Min Act: -0.0000

Data Index: 908234 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.9445. Min Act: -0.0000

Data Index: 665206 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.0475. Min Act: -0.0000

Data Index: 831126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.0673. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8623. Min Act: -0.0000

Data Index: 1180977 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8717. Min Act: -0.0000

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8607. Min Act: -0.0000

Data Index: 759129 (C4 (Web Text))

Max Activating Token Index: 303