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

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

Neuron 3981 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.8231. Min Act: -0.0000

Data Index: 358953 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.5960. Min Act: -0.0000

Data Index: 1137502 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.5808. Min Act: -0.0000

Data Index: 1481718 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.6193. Min Act: -0.0000

Data Index: 1388535 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.3851. Min Act: -0.0000

Data Index: 1311981 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.1186. Min Act: -0.0000

Data Index: 452632 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.4363. Min Act: -0.0000

Data Index: 679275 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.0252. Min Act: -0.0000

Data Index: 1511756 (Python Code)

Max Activating Token Index: 369

Text #8

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.2380. Min Act: -0.0000

Data Index: 1120849 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.3980. Min Act: -0.0000

Data Index: 1627512 (Python Code)

Max Activating Token Index: 250

Text #10

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.9594. Min Act: -0.0000

Data Index: 366660 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.1020. Min Act: -0.0000

Data Index: 772461 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.2659. Min Act: -0.0000

Data Index: 468572 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 5.8231. Min Range: -5.8231

Max Act: 5.0168. Min Act: -0.0000

Data Index: 1080443 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.8862. Min Act: -0.0000

Data Index: 1061931 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.8941. Min Act: -0.0000

Data Index: 896177 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.6339. Min Act: -0.0000

Data Index: 553884 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.9263. Min Act: -0.0000

Data Index: 1542840 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.7235. Min Act: -0.0000

Data Index: 1617753 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 5.8231. Min Range: -5.8231

Max Act: 4.7082. Min Act: -0.0000

Data Index: 1326561 (C4 (Web Text))

Max Activating Token Index: 583