Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 940 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1668. Min Act: -0.0001

Data Index: 924500 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1650. Min Act: -0.0001

Data Index: 731746 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 648119 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1669. Min Act: -0.0001

Data Index: 539520 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1635. Min Act: -0.0001

Data Index: 373886 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1452. Min Act: -0.0000

Data Index: 12464 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1429. Min Act: -0.0000

Data Index: 644670 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1471. Min Act: -0.0001

Data Index: 313 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1501. Min Act: -0.0001

Data Index: 335085 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1424. Min Act: -0.0000

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1389. Min Act: -0.0001

Data Index: 242 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1359. Min Act: -0.0001

Data Index: 227639 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1456. Min Act: -0.0001

Data Index: 115850 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1354. Min Act: -0.0001

Data Index: 191245 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1396. Min Act: -0.0000

Data Index: 811444 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1389. Min Act: -0.0001

Data Index: 314464 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1333. Min Act: -0.0001

Data Index: 697242 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1386. Min Act: -0.0000

Data Index: 49297 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1325. Min Act: -0.0001

Data Index: 791822 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1286. Min Act: -0.0000

Data Index: 384554 (C4 (Web Text))

Max Activating Token Index: 671