Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1756. Min Act: -0.0001

Data Index: 511637 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1708. Min Act: -0.0001

Data Index: 628458 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1602. Min Act: -0.0001

Data Index: 381531 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1242204 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1465. Min Act: -0.0001

Data Index: 509994 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1646. Min Act: -0.0001

Data Index: 968326 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1702. Min Act: -0.0001

Data Index: 478143 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1548. Min Act: -0.0001

Data Index: 211343 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1637. Min Act: -0.0001

Data Index: 403750 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1433. Min Act: -0.0001

Data Index: 161291 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1257713 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1561. Min Act: -0.0001

Data Index: 60402 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1348. Min Act: -0.0001

Data Index: 904163 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1083624 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1410. Min Act: -0.0001

Data Index: 720962 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1520. Min Act: -0.0001

Data Index: 436648 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1429. Min Act: -0.0001

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1469. Min Act: -0.0001

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1464. Min Act: -0.0001

Data Index: 451513 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1166016 (C4 (Web Text))

Max Activating Token Index: 952