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

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

Neuron 45 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: 3.9292. Min Range: -3.9292

Max Act: 3.9292. Min Act: -0.0000

Data Index: 264018 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.9292. Min Range: -3.9292

Max Act: 3.9283. Min Act: -0.0000

Data Index: 1143335 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.9292. Min Range: -3.9292

Max Act: 3.8764. Min Act: -0.0000

Data Index: 439416 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 3.9292. Min Range: -3.9292

Max Act: 3.3570. Min Act: -0.0000

Data Index: 812649 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 3.9292. Min Range: -3.9292

Max Act: 3.2353. Min Act: -0.0000

Data Index: 615272 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.9088. Min Act: -0.0000

Data Index: 651185 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.6529. Min Act: -0.0000

Data Index: 766978 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.6539. Min Act: -0.0000

Data Index: 328272 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.4749. Min Act: -0.0000

Data Index: 297493 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.5201. Min Act: -0.0000

Data Index: 1310182 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.4168. Min Act: -0.0000

Data Index: 175413 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.3698. Min Act: -0.0000

Data Index: 51820 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.2244. Min Act: -0.0000

Data Index: 1264690 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.3167. Min Act: -0.0000

Data Index: 81381 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.2943. Min Act: -0.0000

Data Index: 628814 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 3.9292. Min Range: -3.9292

Max Act: 1.9216. Min Act: -0.0000

Data Index: 647218 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.1324. Min Act: -0.0000

Data Index: 185182 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.2281. Min Act: -0.0000

Data Index: 676739 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.0419. Min Act: -0.0000

Data Index: 33401 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 3.9292. Min Range: -3.9292

Max Act: 2.2550. Min Act: -0.0000

Data Index: 937227 (C4 (Web Text))

Max Activating Token Index: 41