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

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

Neuron 2540 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: 0.4338. Min Range: -0.4338

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4169. Min Act: -0.0001

Data Index: 836429 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4105. Min Act: -0.0002

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3559. Min Act: -0.0001

Data Index: 298702 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3877. Min Act: -0.0002

Data Index: 160397 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4338. Min Act: -0.0001

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3795. Min Act: -0.0002

Data Index: 15769 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3829. Min Act: -0.0001

Data Index: 955155 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3690. Min Act: -0.0001

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1192294 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3518. Min Act: -0.0002

Data Index: 870070 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3525. Min Act: -0.0001

Data Index: 736007 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3212. Min Act: -0.0001

Data Index: 447388 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3509. Min Act: -0.0001

Data Index: 783337 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3354. Min Act: -0.0001

Data Index: 943252 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3467. Min Act: -0.0001

Data Index: 821553 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3308. Min Act: -0.0001

Data Index: 958565 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3253. Min Act: -0.0001

Data Index: 336527 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3222. Min Act: -0.0001

Data Index: 750065 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3251. Min Act: -0.0001

Data Index: 733726 (C4 (Web Text))

Max Activating Token Index: 67