Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.9239. Min Act: -0.0001

Data Index: 336717 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1062548 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8482. Min Act: -0.0001

Data Index: 856679 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1120140 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7715. Min Act: -0.0001

Data Index: 10040 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7533. Min Act: -0.0001

Data Index: 994769 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1201485 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1301959 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7459. Min Act: -0.0001

Data Index: 44299 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1258093 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1345804 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7414. Min Act: -0.0001

Data Index: 476587 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7566. Min Act: -0.0000

Data Index: 977631 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7222. Min Act: -0.0001

Data Index: 580201 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6818. Min Act: -0.0000

Data Index: 305388 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1073034 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6693. Min Act: -0.0000

Data Index: 390548 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6767. Min Act: -0.0000

Data Index: 358703 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1426059 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6805. Min Act: -0.0001

Data Index: 100959 (C4 (Web Text))

Max Activating Token Index: 284