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

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

Neuron 4680 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.5487. Min Act: -0.0000

Data Index: 10809 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1514925 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.6802. Min Act: -0.0000

Data Index: 725728 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1165092 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.6519. Min Act: -0.0000

Data Index: 587771 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5904. Min Act: -0.0000

Data Index: 590406 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5895. Min Act: -0.0000

Data Index: 543423 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1318710 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1644891 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5532. Min Act: -0.0000

Data Index: 589661 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5625. Min Act: -0.0000

Data Index: 817624 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5501. Min Act: -0.0000

Data Index: 966273 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1460475 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5928. Min Act: -0.0000

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1487506 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1356815 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1598841 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1577247 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.5435. Min Act: -0.0000

Data Index: 1618381 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 2.5487. Min Range: -2.5487

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1570282 (Python Code)

Max Activating Token Index: 498