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

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

Neuron 4502 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: 1.4320. Min Range: -1.4320

Max Act: 1.4320. Min Act: -0.0002

Data Index: 158982 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3951. Min Act: -0.0002

Data Index: 742269 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3799. Min Act: -0.0002

Data Index: 360205 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3453. Min Act: -0.0002

Data Index: 1208604 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3485. Min Act: -0.0003

Data Index: 1108572 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3390. Min Act: -0.0002

Data Index: 958821 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3235. Min Act: -0.0002

Data Index: 919550 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3108. Min Act: -0.0002

Data Index: 1296202 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2703. Min Act: -0.0002

Data Index: 817383 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2174. Min Act: -0.0002

Data Index: 446331 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2181. Min Act: -0.0002

Data Index: 277422 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2311. Min Act: -0.0002

Data Index: 769426 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2068. Min Act: -0.0002

Data Index: 191207 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2362. Min Act: -0.0002

Data Index: 597547 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1812. Min Act: -0.0002

Data Index: 576713 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1818. Min Act: -0.0002

Data Index: 585370 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1545. Min Act: -0.0002

Data Index: 1155557 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1621. Min Act: -0.0002

Data Index: 882383 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1471. Min Act: -0.0002

Data Index: 1100213 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1657. Min Act: -0.0002

Data Index: 951388 (C4 (Web Text))

Max Activating Token Index: 952