Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5331 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1287523 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.0315. Min Range: -1.0315

Max Act: 1.0315. Min Act: -0.0000

Data Index: 625278 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4517. Min Act: -0.0000

Data Index: 100566 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1256653 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.6557. Min Act: -0.0000

Data Index: 660480 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.5635. Min Act: -0.0000

Data Index: 727505 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.5273. Min Act: -0.0000

Data Index: 399946 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1125464 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.5073. Min Act: -0.0000

Data Index: 305922 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.3986. Min Act: -0.0000

Data Index: 764771 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1087727 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4862. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4271. Min Act: -0.0000

Data Index: 911760 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4750. Min Act: -0.0000

Data Index: 481455 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1086875 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4953. Min Act: -0.0000

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4494. Min Act: -0.0000

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4478. Min Act: -0.0000

Data Index: 469417 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4436. Min Act: -0.0000

Data Index: 591271 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.0315. Min Range: -1.0315

Max Act: 0.4315. Min Act: -0.0000

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 696