Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2878 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2585. Min Act: -0.0001

Data Index: 450826 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.3281. Min Act: -0.0001

Data Index: 640318 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.4323. Min Act: -0.0001

Data Index: 988393 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1223589 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2490. Min Act: -0.0001

Data Index: 623290 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0605. Min Act: -0.0001

Data Index: 806992 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0500. Min Act: -0.0001

Data Index: 518226 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1139968 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9006. Min Act: -0.0001

Data Index: 711731 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9094. Min Act: -0.0001

Data Index: 952180 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9509. Min Act: -0.0001

Data Index: 627230 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1191527 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8520. Min Act: -0.0001

Data Index: 217670 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8764. Min Act: -0.0001

Data Index: 159285 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1159747 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8350. Min Act: -0.0001

Data Index: 418965 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8314. Min Act: -0.0001

Data Index: 473765 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8619. Min Act: -0.0001

Data Index: 89621 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8776. Min Act: -0.0001

Data Index: 972749 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 1.4323. Min Range: -1.4323

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1320806 (C4 (Web Text))

Max Activating Token Index: 658