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

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

Neuron 3503 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8234. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1163566 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1090478 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6963. Min Act: -0.0000

Data Index: 515656 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1297721 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6375. Min Act: -0.0000

Data Index: 379069 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1461021 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5955. Min Act: -0.0000

Data Index: 395349 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6460. Min Act: -0.0000

Data Index: 363042 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6257. Min Act: -0.0000

Data Index: 297788 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6575. Min Act: -0.0000

Data Index: 657573 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5964. Min Act: -0.0000

Data Index: 49311 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1129463 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5815. Min Act: -0.0000

Data Index: 93076 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6104. Min Act: -0.0000

Data Index: 696078 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5656. Min Act: -0.0000

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1573420 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5813. Min Act: -0.0000

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5724. Min Act: -0.0000

Data Index: 602778 (C4 (Web Text))

Max Activating Token Index: 985