Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3988. Min Act: -0.0001

Data Index: 855745 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4007. Min Act: -0.0001

Data Index: 81150 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3804. Min Act: -0.0001

Data Index: 922893 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0001

Data Index: 867003 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1052567 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3474. Min Act: -0.0001

Data Index: 528339 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3129. Min Act: -0.0000

Data Index: 846014 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3002. Min Act: -0.0001

Data Index: 322988 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1312290 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2979. Min Act: -0.0001

Data Index: 618203 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3005. Min Act: -0.0001

Data Index: 923578 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3041. Min Act: -0.0000

Data Index: 478218 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2879. Min Act: -0.0001

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2865. Min Act: -0.0001

Data Index: 133080 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1152277 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2763. Min Act: -0.0001

Data Index: 465778 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2709. Min Act: -0.0001

Data Index: 1260359 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2699. Min Act: -0.0000

Data Index: 29412 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2764. Min Act: -0.0000

Data Index: 307197 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2749. Min Act: -0.0001

Data Index: 31548 (C4 (Web Text))

Max Activating Token Index: 134