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

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

Neuron 826 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.9974. Min Act: -0.0000

Data Index: 1244009 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1057975 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8336. Min Act: -0.0000

Data Index: 417684 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.5532. Min Act: -0.0000

Data Index: 98748 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.2551. Min Act: -0.0000

Data Index: 1249309 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.1401. Min Act: -0.0000

Data Index: 947024 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8453. Min Act: -0.0000

Data Index: 422108 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.9867. Min Act: -0.0000

Data Index: 1331566 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.1503. Min Act: -0.0000

Data Index: 1240688 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0108. Min Act: -0.0000

Data Index: 8491 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.3154. Min Act: -0.0000

Data Index: 176356 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0177. Min Act: -0.0000

Data Index: 1218722 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.9504. Min Act: -0.0000

Data Index: 770601 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8927. Min Act: -0.0000

Data Index: 225660 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8572. Min Act: -0.0000

Data Index: 696516 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.9420. Min Act: -0.0000

Data Index: 342947 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1306413 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8846. Min Act: -0.0000

Data Index: 70739 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.7820. Min Act: -0.0000

Data Index: 343711 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.7622. Min Act: -0.0000

Data Index: 950430 (C4 (Web Text))

Max Activating Token Index: 776