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

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

Neuron 1430 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.1258. Min Act: -0.0000

Data Index: 864568 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.0927. Min Act: -0.0000

Data Index: 227723 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9877. Min Act: -0.0000

Data Index: 146023 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9907. Min Act: -0.0000

Data Index: 461988 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.0423. Min Act: -0.0000

Data Index: 431491 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9676. Min Act: -0.0000

Data Index: 850937 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.0629. Min Act: -0.0000

Data Index: 978695 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1119568 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9503. Min Act: -0.0000

Data Index: 18957 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1162298 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8336. Min Act: -0.0000

Data Index: 331494 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7437. Min Act: -0.0000

Data Index: 561694 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1214282 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7538. Min Act: -0.0000

Data Index: 608956 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7611. Min Act: -0.0000

Data Index: 2860 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7505. Min Act: -0.0000

Data Index: 184555 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8199. Min Act: -0.0000

Data Index: 901117 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7275. Min Act: -0.0000

Data Index: 279248 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1255946 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1152653 (C4 (Web Text))

Max Activating Token Index: 204