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

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

Neuron 670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1219783 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0504. Min Act: -0.0000

Data Index: 100321 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0425. Min Act: -0.0000

Data Index: 465843 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1184928 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0388. Min Act: -0.0000

Data Index: 690425 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0361. Min Act: -0.0000

Data Index: 348109 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0375. Min Act: -0.0000

Data Index: 558773 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0359. Min Act: -0.0000

Data Index: 581357 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0343. Min Act: -0.0000

Data Index: 499046 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1012543 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0341. Min Act: -0.0000

Data Index: 824629 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1217606 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0338. Min Act: -0.0000

Data Index: 619461 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0349. Min Act: -0.0000

Data Index: 161817 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0409. Min Act: -0.0000

Data Index: 418114 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1525538 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0343. Min Act: -0.0000

Data Index: 983227 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0331. Min Act: -0.0000

Data Index: 764961 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0331. Min Act: -0.0000

Data Index: 672025 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1046980 (C4 (Web Text))

Max Activating Token Index: 958