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

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

Neuron 5134 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0002

Data Index: 264533 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0002

Data Index: 280038 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0458. Min Act: -0.0002

Data Index: 329680 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1294681 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1400652 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0405. Min Act: -0.0002

Data Index: 305048 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0442. Min Act: -0.0002

Data Index: 95768 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1405173 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0429. Min Act: -0.0002

Data Index: 82670 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1240886 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0342. Min Act: -0.0002

Data Index: 145800 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1171517 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0394. Min Act: -0.0002

Data Index: 594441 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0424. Min Act: -0.0002

Data Index: 542048 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0406. Min Act: -0.0002

Data Index: 415052 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1140724 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1289264 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1263501 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0398. Min Act: -0.0002

Data Index: 243027 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0398. Min Act: -0.0002

Data Index: 985154 (C4 (Web Text))

Max Activating Token Index: 556