Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2334. Min Range: -3.2334

Max Act: 3.2334. Min Act: -0.0000

Data Index: 1326361 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.8384. Min Act: -0.0000

Data Index: 466654 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.8974. Min Act: -0.0000

Data Index: 1202247 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.8389. Min Act: -0.0000

Data Index: 200924 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.9768. Min Act: -0.0000

Data Index: 135571 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.9719. Min Act: -0.0000

Data Index: 372331 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.8116. Min Act: -0.0000

Data Index: 1138642 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.6493. Min Act: -0.0000

Data Index: 432726 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7744. Min Act: -0.0000

Data Index: 1213324 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7825. Min Act: -0.0000

Data Index: 682551 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.9033. Min Act: -0.0000

Data Index: 306364 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1266720 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7499. Min Act: -0.0000

Data Index: 596532 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7641. Min Act: -0.0000

Data Index: 424556 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7597. Min Act: -0.0000

Data Index: 508911 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7584. Min Act: -0.0000

Data Index: 182088 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.6194. Min Act: -0.0000

Data Index: 607794 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7372. Min Act: -0.0000

Data Index: 593803 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.7447. Min Act: -0.0000

Data Index: 406254 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.2334. Min Range: -3.2334

Max Act: 2.5916. Min Act: -0.0000

Data Index: 1223939 (C4 (Web Text))

Max Activating Token Index: 362