Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1772 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.5247. Min Act: -0.0001

Data Index: 416273 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.4659. Min Act: -0.0001

Data Index: 447840 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.4673. Min Act: -0.0001

Data Index: 1264144 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.2573. Min Act: -0.0001

Data Index: 143779 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.2751. Min Act: -0.0001

Data Index: 894059 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.3013. Min Act: -0.0001

Data Index: 244282 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.0884. Min Act: -0.0001

Data Index: 601032 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1490. Min Act: -0.0001

Data Index: 401490 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1985. Min Act: -0.0001

Data Index: 1320302 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.2246. Min Act: -0.0001

Data Index: 628777 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1355362 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.5247. Min Range: -1.5247

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1353937 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.5247. Min Range: -1.5247

Max Act: 0.9899. Min Act: -0.0001

Data Index: 100670 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1381. Min Act: -0.0001

Data Index: 396968 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1767. Min Act: -0.0001

Data Index: 528500 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1145. Min Act: -0.0001

Data Index: 1154839 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1603. Min Act: -0.0001

Data Index: 315643 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.1349. Min Act: -0.0001

Data Index: 293818 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.0525. Min Act: -0.0001

Data Index: 989326 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.5247. Min Range: -1.5247

Max Act: 1.0608. Min Act: -0.0001

Data Index: 1079697 (C4 (Web Text))

Max Activating Token Index: 464