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

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

Neuron 1790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4571. Min Act: -0.0001

Data Index: 1097110 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5096. Min Act: -0.0001

Data Index: 872285 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4643. Min Act: -0.0001

Data Index: 1030956 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4991. Min Act: -0.0001

Data Index: 184484 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5279. Min Act: -0.0001

Data Index: 721639 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4436. Min Act: -0.0001

Data Index: 850038 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3904. Min Act: -0.0001

Data Index: 957354 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4303. Min Act: -0.0001

Data Index: 412100 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4528. Min Act: -0.0001

Data Index: 1357273 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.6313. Min Act: -0.0001

Data Index: 444406 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1096768 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4252. Min Act: -0.0001

Data Index: 107231 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4517. Min Act: -0.0001

Data Index: 1002915 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3782. Min Act: -0.0001

Data Index: 509960 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3262. Min Act: -0.0001

Data Index: 692145 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1031987 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3218. Min Act: -0.0001

Data Index: 236559 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.4165. Min Act: -0.0001

Data Index: 1253268 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3876. Min Act: -0.0001

Data Index: 676418 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.3735. Min Act: -0.0001

Data Index: 592587 (C4 (Web Text))

Max Activating Token Index: 410