Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 9 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.2506. Min Act: 0.0001

Data Index: 157000 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8892. Min Act: 0.0001

Data Index: 835208 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1012797 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.7686. Min Act: -0.0000

Data Index: 974715 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1297738 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6949. Min Act: -0.0000

Data Index: 18410 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.7298. Min Act: 0.0000

Data Index: 136568 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.7191. Min Act: 0.0000

Data Index: 321892 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6823. Min Act: -0.0000

Data Index: 630017 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6989. Min Act: -0.0000

Data Index: 448547 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6484. Min Act: 0.0001

Data Index: 130515 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.7122. Min Act: -0.0000

Data Index: 432358 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6835. Min Act: -0.0000

Data Index: 829553 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6731. Min Act: 0.0000

Data Index: 210374 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6735. Min Act: -0.0000

Data Index: 656232 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6548. Min Act: -0.0000

Data Index: 946088 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6386. Min Act: -0.0000

Data Index: 731761 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1175471 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6398. Min Act: 0.0000

Data Index: 681012 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.6335. Min Act: 0.0000

Data Index: 822992 (C4 (Web Text))

Max Activating Token Index: 593