Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 225 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0698. Min Range: -1.0698

Max Act: 1.0698. Min Act: -0.0001

Data Index: 367305 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9712. Min Act: -0.0001

Data Index: 757847 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.0698. Min Range: -1.0698

Max Act: 1.0131. Min Act: -0.0001

Data Index: 561351 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9469. Min Act: -0.0001

Data Index: 305208 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9464. Min Act: -0.0001

Data Index: 442241 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1201698 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9297. Min Act: -0.0001

Data Index: 641303 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9152. Min Act: -0.0001

Data Index: 99946 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9027. Min Act: -0.0001

Data Index: 452911 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8771. Min Act: -0.0001

Data Index: 258780 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.9053. Min Act: -0.0001

Data Index: 404889 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8842. Min Act: -0.0001

Data Index: 999468 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8601. Min Act: -0.0001

Data Index: 9460 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1255398 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8264. Min Act: -0.0001

Data Index: 860793 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8654. Min Act: -0.0001

Data Index: 944477 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8741. Min Act: -0.0001

Data Index: 297506 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8440. Min Act: -0.0001

Data Index: 816457 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8768. Min Act: -0.0001

Data Index: 156839 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.0698. Min Range: -1.0698

Max Act: 0.8160. Min Act: -0.0001

Data Index: 510226 (C4 (Web Text))

Max Activating Token Index: 940