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

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

Neuron 611 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: 0.5963. Min Range: -0.5963

Max Act: 0.5761. Min Act: -0.0000

Data Index: 65397 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1201136 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0000

Data Index: 396385 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1331984 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5205. Min Act: -0.0000

Data Index: 512843 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4585. Min Act: -0.0000

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4795. Min Act: -0.0000

Data Index: 589820 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1125060 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1242256 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4516. Min Act: -0.0000

Data Index: 272906 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1156612 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4297. Min Act: -0.0000

Data Index: 642961 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4173. Min Act: -0.0000

Data Index: 421505 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4219. Min Act: -0.0000

Data Index: 708299 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4067. Min Act: -0.0000

Data Index: 751250 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1321401 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4223. Min Act: -0.0000

Data Index: 258519 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1346253 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4011. Min Act: -0.0000

Data Index: 633344 (C4 (Web Text))

Max Activating Token Index: 117