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

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

Neuron 4000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5579. Min Range: -2.5579

Max Act: 2.5579. Min Act: -0.0000

Data Index: 1157998 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 2.5579. Min Range: -2.5579

Max Act: 2.4856. Min Act: -0.0001

Data Index: 566734 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 2.5579. Min Range: -2.5579

Max Act: 2.2107. Min Act: -0.0001

Data Index: 785253 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1157322 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.7691. Min Act: -0.0000

Data Index: 104412 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.6511. Min Act: -0.0000

Data Index: 120844 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.6285. Min Act: -0.0001

Data Index: 1149498 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1355014 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1358805 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.6191. Min Act: -0.0001

Data Index: 627768 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.4856. Min Act: -0.0001

Data Index: 1053912 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.4571. Min Act: -0.0001

Data Index: 1330991 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1169989 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1358535 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.3582. Min Act: -0.0000

Data Index: 838510 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.2951. Min Act: -0.0001

Data Index: 618416 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.2791. Min Act: -0.0001

Data Index: 978688 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.2765. Min Act: -0.0001

Data Index: 105948 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.2589. Min Act: -0.0001

Data Index: 392179 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 2.5579. Min Range: -2.5579

Max Act: 1.3570. Min Act: -0.0001

Data Index: 139101 (C4 (Web Text))

Max Activating Token Index: 1019