Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 644 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0003

Data Index: 887213 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0419. Min Act: -0.0002

Data Index: 782419 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0419. Min Act: -0.0003

Data Index: 847123 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0411. Min Act: -0.0003

Data Index: 222059 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0399. Min Act: -0.0003

Data Index: 295320 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0385. Min Act: -0.0003

Data Index: 910143 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1096100 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1010675 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0405. Min Act: -0.0003

Data Index: 585186 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1196181 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0380. Min Act: -0.0003

Data Index: 47818 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1211060 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0367. Min Act: -0.0003

Data Index: 57382 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1146033 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0370. Min Act: -0.0003

Data Index: 694963 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0365. Min Act: -0.0003

Data Index: 128663 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0349. Min Act: -0.0003

Data Index: 127512 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0347. Min Act: -0.0002

Data Index: 67932 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1063919 (C4 (Web Text))

Max Activating Token Index: 357