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

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

Neuron 1180 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: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0001

Data Index: 748759 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1836. Min Act: -0.0000

Data Index: 188535 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1686. Min Act: -0.0000

Data Index: 347703 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1312154 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1710. Min Act: -0.0001

Data Index: 593615 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1635. Min Act: -0.0001

Data Index: 86111 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1603. Min Act: -0.0000

Data Index: 306853 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1579. Min Act: -0.0001

Data Index: 441114 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1573. Min Act: -0.0000

Data Index: 334445 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1047684 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1240095 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1568. Min Act: -0.0000

Data Index: 847003 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1555. Min Act: -0.0001

Data Index: 13826 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1486. Min Act: -0.0000

Data Index: 400750 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1480. Min Act: -0.0000

Data Index: 744241 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1471. Min Act: -0.0000

Data Index: 892598 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1465. Min Act: -0.0000

Data Index: 630890 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1129978 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1199712 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1422. Min Act: -0.0001

Data Index: 652576 (C4 (Web Text))

Max Activating Token Index: 685