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

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

Neuron 2556 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1002432 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3236. Min Act: -0.0000

Data Index: 235556 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3217. Min Act: -0.0000

Data Index: 759576 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3066. Min Act: -0.0000

Data Index: 278451 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2886. Min Act: -0.0001

Data Index: 700140 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2815. Min Act: -0.0001

Data Index: 922214 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2655. Min Act: -0.0000

Data Index: 32656 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2703. Min Act: -0.0001

Data Index: 1255995 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2661. Min Act: -0.0000

Data Index: 893256 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2655. Min Act: -0.0000

Data Index: 301268 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2744. Min Act: -0.0000

Data Index: 755237 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2631. Min Act: 0.0000

Data Index: 784271 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2638. Min Act: -0.0000

Data Index: 667020 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2486. Min Act: -0.0001

Data Index: 266972 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2476. Min Act: -0.0000

Data Index: 608006 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2403. Min Act: -0.0000

Data Index: 693462 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2463. Min Act: -0.0000

Data Index: 701776 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2441. Min Act: -0.0001

Data Index: 816877 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2397. Min Act: -0.0000

Data Index: 70231 (C4 (Web Text))

Max Activating Token Index: 615