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

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

Neuron 2852 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2720. Min Act: -0.0002

Data Index: 1354218 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2860. Min Act: -0.0002

Data Index: 685052 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2676. Min Act: -0.0002

Data Index: 910435 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2533. Min Act: -0.0003

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2738. Min Act: -0.0002

Data Index: 612295 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2322. Min Act: -0.0002

Data Index: 622939 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2369. Min Act: -0.0002

Data Index: 268833 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2197. Min Act: -0.0002

Data Index: 1298974 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2334. Min Act: -0.0002

Data Index: 441594 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2218. Min Act: -0.0002

Data Index: 881475 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2124. Min Act: -0.0002

Data Index: 1149964 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2027. Min Act: -0.0002

Data Index: 489131 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2130. Min Act: -0.0002

Data Index: 221391 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1902. Min Act: -0.0002

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2093. Min Act: -0.0002

Data Index: 293222 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2056. Min Act: -0.0003

Data Index: 1060950 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1769. Min Act: -0.0002

Data Index: 345460 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1588. Min Act: -0.0003

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1790. Min Act: -0.0003

Data Index: 740782 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1361. Min Act: -0.0002

Data Index: 958890 (C4 (Web Text))

Max Activating Token Index: 275