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

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

Neuron 557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0398. Min Act: -0.0001

Data Index: 380155 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0001

Data Index: 778587 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1112145 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0317. Min Act: -0.0002

Data Index: 679317 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0303. Min Act: -0.0001

Data Index: 416723 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0315. Min Act: -0.0001

Data Index: 818067 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1008226 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1309726 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0306. Min Act: -0.0001

Data Index: 275517 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0293. Min Act: -0.0001

Data Index: 247944 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0299. Min Act: -0.0001

Data Index: 136374 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0300. Min Act: -0.0001

Data Index: 812649 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0289. Min Act: -0.0001

Data Index: 39119 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1001510 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0290. Min Act: -0.0001

Data Index: 809059 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1003739 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1129593 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1115652 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0278. Min Act: -0.0001

Data Index: 111929 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0276. Min Act: -0.0001

Data Index: 380389 (C4 (Web Text))

Max Activating Token Index: 943