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

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

Neuron 3190 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: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0003

Data Index: 220130 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0320. Min Act: -0.0002

Data Index: 449906 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0312. Min Act: -0.0002

Data Index: 723168 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0313. Min Act: -0.0003

Data Index: 287786 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1181265 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0307. Min Act: -0.0002

Data Index: 328001 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0307. Min Act: -0.0002

Data Index: 264467 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1197206 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1007342 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0297. Min Act: -0.0002

Data Index: 72961 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0297. Min Act: -0.0002

Data Index: 735146 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0002

Data Index: 311821 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0299. Min Act: -0.0002

Data Index: 798029 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0002

Data Index: 408880 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0296. Min Act: -0.0002

Data Index: 500109 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0285. Min Act: -0.0002

Data Index: 641813 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0002

Data Index: 952682 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0002

Data Index: 283234 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0287. Min Act: -0.0002

Data Index: 67947 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0281. Min Act: -0.0002

Data Index: 103397 (C4 (Web Text))

Max Activating Token Index: 762