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

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

Neuron 3223 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.8255. Min Act: -0.0000

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.4681. Min Act: -0.0000

Data Index: 309665 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.4705. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.4156. Min Act: -0.0000

Data Index: 34532 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.4041. Min Act: -0.0000

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3987. Min Act: -0.0000

Data Index: 147257 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.4260. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3761. Min Act: -0.0000

Data Index: 803518 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3625. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3625. Min Act: -0.0000

Data Index: 837992 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3662. Min Act: -0.0000

Data Index: 871691 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3424. Min Act: 0.0000

Data Index: 464387 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3389. Min Act: -0.0000

Data Index: 526497 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3589. Min Act: -0.0000

Data Index: 761988 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3539. Min Act: -0.0000

Data Index: 945933 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1049343 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3528. Min Act: -0.0000

Data Index: 237619 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3532. Min Act: -0.0000

Data Index: 464047 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3532. Min Act: -0.0000

Data Index: 346954 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.3645. Min Act: -0.0000

Data Index: 630926 (C4 (Web Text))

Max Activating Token Index: 238