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

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

Neuron 2969 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1602. Min Act: -0.0001

Data Index: 478049 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1184609 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1005481 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1706. Min Act: -0.0001

Data Index: 668015 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1429. Min Act: -0.0001

Data Index: 877524 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1600. Min Act: -0.0001

Data Index: 501514 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1697. Min Act: -0.0001

Data Index: 508506 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1619. Min Act: -0.0001

Data Index: 176641 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1475. Min Act: -0.0001

Data Index: 959691 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1464. Min Act: -0.0001

Data Index: 873811 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1111801 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1297942 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1319. Min Act: -0.0001

Data Index: 193651 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1196967 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1200991 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1059428 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1463. Min Act: -0.0001

Data Index: 726321 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1354. Min Act: -0.0001

Data Index: 914800 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1340. Min Act: -0.0001

Data Index: 183671 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1190873 (C4 (Web Text))

Max Activating Token Index: 138