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

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

Neuron 3562 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 748801 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0582. Min Act: -0.0002

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0536. Min Act: -0.0002

Data Index: 4421 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0462. Min Act: -0.0002

Data Index: 827658 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1166087 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0455. Min Act: -0.0001

Data Index: 894403 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0455. Min Act: -0.0002

Data Index: 381689 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0444. Min Act: -0.0002

Data Index: 682745 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0440. Min Act: -0.0001

Data Index: 622674 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0438. Min Act: -0.0002

Data Index: 369523 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0438. Min Act: -0.0002

Data Index: 130994 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0429. Min Act: -0.0001

Data Index: 524825 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0001

Data Index: 770107 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0414. Min Act: -0.0002

Data Index: 671167 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1324422 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1320545 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0002

Data Index: 442423 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1033021 (C4 (Web Text))

Max Activating Token Index: 1009