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

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

Neuron 6010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1152. Min Range: -1.1152

Max Act: 1.1152. Min Act: -0.0000

Data Index: 20413 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1035081 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.8727. Min Act: -0.0000

Data Index: 492182 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7714. Min Act: -0.0000

Data Index: 968105 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6853. Min Act: -0.0000

Data Index: 506387 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.7044. Min Act: -0.0000

Data Index: 495964 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1199732 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6671. Min Act: -0.0000

Data Index: 276305 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6541. Min Act: -0.0000

Data Index: 904144 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1233164 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6184. Min Act: -0.0000

Data Index: 146772 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1255960 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5545. Min Act: -0.0000

Data Index: 933635 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5951. Min Act: -0.0000

Data Index: 38858 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1242193 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5434. Min Act: -0.0000

Data Index: 782944 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5370. Min Act: -0.0000

Data Index: 964007 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.4988. Min Act: -0.0000

Data Index: 276650 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1183966 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.1152. Min Range: -1.1152

Max Act: 0.5041. Min Act: -0.0000

Data Index: 230702 (C4 (Web Text))

Max Activating Token Index: 247