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

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

Neuron 5041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.7967. Min Act: -0.0000

Data Index: 1231232 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.4134. Min Act: -0.0000

Data Index: 248661 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.5826. Min Act: -0.0000

Data Index: 530483 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.5485. Min Act: -0.0000

Data Index: 11699 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.4967. Min Act: -0.0000

Data Index: 1344585 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.6370. Min Act: -0.0000

Data Index: 240311 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.6255. Min Act: -0.0000

Data Index: 271196 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.5688. Min Act: -0.0000

Data Index: 1343199 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.4016. Min Act: -0.0000

Data Index: 928467 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.4023. Min Act: -0.0000

Data Index: 727944 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.0304. Min Act: -0.0000

Data Index: 288481 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.1787. Min Act: -0.0000

Data Index: 593236 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.3403. Min Act: -0.0000

Data Index: 815033 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.0741. Min Act: -0.0000

Data Index: 1261657 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.3685. Min Act: -0.0000

Data Index: 374783 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 4.7967. Min Range: -4.7967

Max Act: 3.9943. Min Act: -0.0000

Data Index: 423191 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.2560. Min Act: -0.0000

Data Index: 777328 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.2714. Min Act: -0.0000

Data Index: 671857 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.0171. Min Act: -0.0000

Data Index: 81409 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 4.7967. Min Range: -4.7967

Max Act: 4.0273. Min Act: -0.0000

Data Index: 66084 (C4 (Web Text))

Max Activating Token Index: 845