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

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

Neuron 1504 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: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0000

Data Index: 484469 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1174206 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0820. Min Act: -0.0000

Data Index: 557422 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0846. Min Act: -0.0000

Data Index: 847179 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0811. Min Act: -0.0001

Data Index: 762338 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0759. Min Act: -0.0001

Data Index: 142089 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0700. Min Act: -0.0000

Data Index: 410530 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0800. Min Act: -0.0000

Data Index: 51015 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0669. Min Act: -0.0000

Data Index: 657774 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0683. Min Act: -0.0001

Data Index: 778502 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1239506 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1335517 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1309494 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0636. Min Act: -0.0000

Data Index: 355370 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0638. Min Act: -0.0001

Data Index: 740767 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1488820 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0613. Min Act: -0.0000

Data Index: 517916 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1561462 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1545665 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.0592. Min Act: -0.0000

Data Index: 769861 (C4 (Web Text))

Max Activating Token Index: 1001