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

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

Neuron 4547 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1345914 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1002296 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1088113 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1203150 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6553. Min Act: -0.0000

Data Index: 4980 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6067. Min Act: -0.0000

Data Index: 723818 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5950. Min Act: -0.0000

Data Index: 45426 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5833. Min Act: -0.0000

Data Index: 157160 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5897. Min Act: -0.0000

Data Index: 686725 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5727. Min Act: -0.0000

Data Index: 144137 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1640262 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5438. Min Act: -0.0000

Data Index: 322373 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5465. Min Act: -0.0000

Data Index: 728366 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5089. Min Act: -0.0000

Data Index: 525312 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1383671 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5535. Min Act: -0.0000

Data Index: 83374 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1008567 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1096451 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5130. Min Act: -0.0000

Data Index: 143487 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1145255 (C4 (Web Text))

Max Activating Token Index: 808