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

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

Neuron 4779 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1190003 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4527. Min Act: -0.0000

Data Index: 278576 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4241. Min Act: -0.0000

Data Index: 690467 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3920. Min Act: -0.0000

Data Index: 907894 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4021. Min Act: -0.0000

Data Index: 415925 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3865. Min Act: -0.0000

Data Index: 452585 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3669. Min Act: -0.0000

Data Index: 772302 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4087. Min Act: -0.0000

Data Index: 139439 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1335093 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3386. Min Act: -0.0000

Data Index: 658498 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1161650 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1055612 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1349791 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3327. Min Act: -0.0000

Data Index: 722400 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3417. Min Act: -0.0000

Data Index: 388460 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3403. Min Act: -0.0000

Data Index: 740956 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3402. Min Act: -0.0000

Data Index: 35387 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3395. Min Act: -0.0000

Data Index: 408440 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3474. Min Act: -0.0000

Data Index: 393940 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 139