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

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

Neuron 2093 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: 2.2274. Min Range: -2.2274

Max Act: 2.1035. Min Act: -0.0000

Data Index: 362460 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1030241 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.2274. Min Act: -0.0000

Data Index: 500868 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0950. Min Act: -0.0000

Data Index: 427208 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0808. Min Act: -0.0000

Data Index: 969415 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9876. Min Act: -0.0000

Data Index: 116456 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1004274 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1011148 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9605. Min Act: -0.0000

Data Index: 375659 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9332. Min Act: -0.0000

Data Index: 1007202 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1169255 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9061. Min Act: -0.0000

Data Index: 662464 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8747. Min Act: -0.0000

Data Index: 310131 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8730. Min Act: -0.0000

Data Index: 845373 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9715. Min Act: -0.0000

Data Index: 572665 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8381. Min Act: -0.0000

Data Index: 46248 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7787. Min Act: -0.0000

Data Index: 487503 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1256808 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7531. Min Act: -0.0000

Data Index: 463461 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1170875 (C4 (Web Text))

Max Activating Token Index: 670