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

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

Neuron 4251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0893. Min Act: -0.0002

Data Index: 144938 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0043. Min Act: -0.0003

Data Index: 780158 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9920. Min Act: -0.0002

Data Index: 1103971 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9824. Min Act: -0.0002

Data Index: 78290 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9369. Min Act: -0.0003

Data Index: 216246 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9498. Min Act: -0.0003

Data Index: 847134 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9452. Min Act: -0.0003

Data Index: 1050974 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9279. Min Act: -0.0003

Data Index: 554386 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8996. Min Act: -0.0003

Data Index: 381712 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8933. Min Act: -0.0003

Data Index: 375380 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9105. Min Act: -0.0002

Data Index: 77443 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8751. Min Act: -0.0003

Data Index: 931844 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8377. Min Act: -0.0003

Data Index: 431960 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8918. Min Act: -0.0003

Data Index: 521706 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8399. Min Act: -0.0002

Data Index: 767735 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8621. Min Act: -0.0003

Data Index: 1296825 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8414. Min Act: -0.0003

Data Index: 1329803 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8417. Min Act: -0.0003

Data Index: 1167818 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8619. Min Act: -0.0002

Data Index: 774533 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8787. Min Act: -0.0003

Data Index: 1070415 (C4 (Web Text))

Max Activating Token Index: 670