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

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

Neuron 3830 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.3436. Min Act: -0.0001

Data Index: 238851 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2661. Min Act: -0.0001

Data Index: 817537 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2916. Min Act: -0.0001

Data Index: 842768 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2819. Min Act: -0.0001

Data Index: 27886 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2467. Min Act: -0.0001

Data Index: 217774 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2342. Min Act: -0.0001

Data Index: 1344652 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1656. Min Act: -0.0001

Data Index: 1083029 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1452. Min Act: -0.0001

Data Index: 571200 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1171636 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1158. Min Act: -0.0001

Data Index: 958245 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0103. Min Act: -0.0001

Data Index: 17358 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1109. Min Act: -0.0001

Data Index: 518575 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0736. Min Act: -0.0001

Data Index: 311816 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1467. Min Act: -0.0001

Data Index: 144782 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1466. Min Act: -0.0001

Data Index: 603570 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0381. Min Act: -0.0001

Data Index: 187869 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0598. Min Act: -0.0001

Data Index: 361288 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0274. Min Act: -0.0001

Data Index: 446211 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2087. Min Act: -0.0001

Data Index: 454270 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0309. Min Act: -0.0001

Data Index: 973589 (C4 (Web Text))

Max Activating Token Index: 602