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

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

Neuron 5292 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: 0.0543. Min Range: -0.0543

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1108569 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1156092 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1260185 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0434. Min Act: -0.0001

Data Index: 437336 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0433. Min Act: -0.0001

Data Index: 597023 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0378. Min Act: -0.0001

Data Index: 764142 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0370. Min Act: -0.0001

Data Index: 410203 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0331. Min Act: -0.0001

Data Index: 453092 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0356. Min Act: -0.0001

Data Index: 600468 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1346438 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1226051 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0360. Min Act: -0.0001

Data Index: 559498 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0349. Min Act: -0.0001

Data Index: 680801 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0326. Min Act: -0.0001

Data Index: 117817 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0355. Min Act: -0.0001

Data Index: 695263 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0323. Min Act: -0.0002

Data Index: 305693 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1133227 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0340. Min Act: -0.0001

Data Index: 838213 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0313. Min Act: -0.0001

Data Index: 517295 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0345. Min Act: -0.0001

Data Index: 142155 (C4 (Web Text))

Max Activating Token Index: 800