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

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

Neuron 3527 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9256. Min Range: -8.9256

Max Act: 8.9256. Min Act: -0.0000

Data Index: 858375 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 8.9256. Min Range: -8.9256

Max Act: 7.5643. Min Act: -0.0000

Data Index: 792714 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 8.9256. Min Range: -8.9256

Max Act: 7.1272. Min Act: -0.0000

Data Index: 652440 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.8577. Min Act: -0.0000

Data Index: 1334028 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 8.9256. Min Range: -8.9256

Max Act: 7.3746. Min Act: -0.0000

Data Index: 1230689 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.9309. Min Act: -0.0000

Data Index: 1358868 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.3838. Min Act: -0.0000

Data Index: 634746 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.8576. Min Act: -0.0000

Data Index: 632180 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.9803. Min Act: -0.0000

Data Index: 59052 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.5462. Min Act: -0.0000

Data Index: 379459 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.0879. Min Act: -0.0000

Data Index: 689357 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.3510. Min Act: -0.0000

Data Index: 204253 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.0859. Min Act: -0.0000

Data Index: 1080530 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.1471. Min Act: -0.0000

Data Index: 952122 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.0965. Min Act: -0.0000

Data Index: 734126 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 8.9256. Min Range: -8.9256

Max Act: 5.9008. Min Act: -0.0000

Data Index: 148621 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.0919. Min Act: -0.0000

Data Index: 369472 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 8.9256. Min Range: -8.9256

Max Act: 6.0300. Min Act: -0.0000

Data Index: 661339 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 8.9256. Min Range: -8.9256

Max Act: 5.8007. Min Act: -0.0000

Data Index: 683760 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 8.9256. Min Range: -8.9256

Max Act: 5.9080. Min Act: -0.0000

Data Index: 235011 (C4 (Web Text))

Max Activating Token Index: 398