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

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

Neuron 4131 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: 1.1950. Min Range: -1.1950

Max Act: 1.1950. Min Act: -0.0000

Data Index: 315546 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1161637 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9423. Min Act: -0.0000

Data Index: 436465 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.6976. Min Act: -0.0000

Data Index: 991226 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.6330. Min Act: -0.0000

Data Index: 610327 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.6261. Min Act: -0.0000

Data Index: 474591 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5694. Min Act: -0.0000

Data Index: 584134 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5908. Min Act: -0.0000

Data Index: 373270 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1238207 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5832. Min Act: -0.0000

Data Index: 745289 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5366. Min Act: -0.0000

Data Index: 502792 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5671. Min Act: -0.0000

Data Index: 142430 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1278656 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5270. Min Act: -0.0000

Data Index: 795077 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1248404 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5306. Min Act: -0.0000

Data Index: 830868 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5093. Min Act: -0.0000

Data Index: 64287 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5127. Min Act: -0.0000

Data Index: 529365 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.5573. Min Act: -0.0000

Data Index: 167365 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.4638. Min Act: -0.0000

Data Index: 734694 (C4 (Web Text))

Max Activating Token Index: 109