Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3526 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7372. Min Range: -6.7372

Max Act: 6.7372. Min Act: -0.0000

Data Index: 1078257 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.5988. Min Act: -0.0000

Data Index: 968654 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.6671. Min Act: -0.0000

Data Index: 1285563 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.1260. Min Act: -0.0000

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.2767. Min Act: -0.0000

Data Index: 1656271 (Python Code)

Max Activating Token Index: 781

Text #5

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.1218. Min Act: -0.0000

Data Index: 1475442 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 6.7372. Min Range: -6.7372

Max Act: 4.1093. Min Act: -0.0000

Data Index: 1324691 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.8049. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.8071. Min Act: -0.0000

Data Index: 226589 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.8156. Min Act: -0.0000

Data Index: 446325 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.7384. Min Act: -0.0000

Data Index: 327446 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.6802. Min Act: -0.0000

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.6384. Min Act: -0.0000

Data Index: 796126 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.6174. Min Act: -0.0000

Data Index: 898726 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.6080. Min Act: -0.0000

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.5962. Min Act: -0.0000

Data Index: 737367 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.5864. Min Act: -0.0000

Data Index: 687019 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.4096. Min Act: -0.0000

Data Index: 1225384 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.5361. Min Act: -0.0000

Data Index: 927294 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 6.7372. Min Range: -6.7372

Max Act: 3.5067. Min Act: -0.0000

Data Index: 1317801 (C4 (Web Text))

Max Activating Token Index: 619