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

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

Neuron 3427 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: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0002

Data Index: 909791 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0301. Min Act: -0.0002

Data Index: 53006 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1079248 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1319164 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0297. Min Act: -0.0002

Data Index: 347387 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0288. Min Act: -0.0002

Data Index: 933885 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0290. Min Act: -0.0002

Data Index: 664666 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1009054 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0282. Min Act: -0.0002

Data Index: 685824 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0282. Min Act: -0.0002

Data Index: 162003 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1444089 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0280. Min Act: -0.0002

Data Index: 548039 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0276. Min Act: -0.0002

Data Index: 188067 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0275. Min Act: -0.0002

Data Index: 643229 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0275. Min Act: -0.0002

Data Index: 137308 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0269. Min Act: -0.0002

Data Index: 758549 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0268. Min Act: -0.0002

Data Index: 670628 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0267. Min Act: -0.0002

Data Index: 943912 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0264. Min Act: -0.0002

Data Index: 862964 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0262. Min Act: -0.0002

Data Index: 368630 (C4 (Web Text))

Max Activating Token Index: 70