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

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

Neuron 3709 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1194007 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0388. Min Act: -0.0002

Data Index: 71455 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0381. Min Act: -0.0002

Data Index: 890632 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1070390 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0350. Min Act: -0.0002

Data Index: 809432 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0341. Min Act: -0.0002

Data Index: 215782 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0364. Min Act: -0.0002

Data Index: 570686 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1019309 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0361. Min Act: -0.0002

Data Index: 465264 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0360. Min Act: -0.0002

Data Index: 208623 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0328. Min Act: -0.0002

Data Index: 445659 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1047056 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0334. Min Act: -0.0002

Data Index: 798309 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0301. Min Act: -0.0002

Data Index: 601424 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0323. Min Act: -0.0002

Data Index: 825125 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1100170 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1075274 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1304573 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0303. Min Act: -0.0002

Data Index: 199329 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0313. Min Act: -0.0002

Data Index: 942637 (C4 (Web Text))

Max Activating Token Index: 149