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

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

Neuron 548 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3584. Min Act: -0.0004

Data Index: 592087 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3863. Min Act: -0.0004

Data Index: 496475 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3643. Min Act: -0.0004

Data Index: 1096215 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3368. Min Act: -0.0004

Data Index: 571411 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.4280. Min Act: -0.0004

Data Index: 583585 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3373. Min Act: -0.0004

Data Index: 447396 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3592. Min Act: -0.0004

Data Index: 651085 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3721. Min Act: -0.0004

Data Index: 1058762 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3591. Min Act: -0.0004

Data Index: 1346953 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3553. Min Act: -0.0004

Data Index: 765588 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.4171. Min Act: -0.0004

Data Index: 1236617 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3317. Min Act: -0.0004

Data Index: 1309629 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3188. Min Act: -0.0004

Data Index: 303878 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3565. Min Act: -0.0004

Data Index: 893660 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3720. Min Act: -0.0004

Data Index: 581709 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3601. Min Act: -0.0004

Data Index: 696906 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3575. Min Act: -0.0004

Data Index: 848826 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3712. Min Act: -0.0004

Data Index: 1239466 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3943. Min Act: -0.0004

Data Index: 769534 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.4205. Min Act: -0.0004

Data Index: 774879 (C4 (Web Text))

Max Activating Token Index: 517