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

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

Neuron 1665 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1979. Min Act: -0.0001

Data Index: 786873 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.2002. Min Act: -0.0001

Data Index: 478669 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1865. Min Act: -0.0001

Data Index: 238158 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1933. Min Act: -0.0001

Data Index: 355474 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1762. Min Act: -0.0001

Data Index: 863364 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1667. Min Act: -0.0001

Data Index: 400952 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1701. Min Act: -0.0001

Data Index: 275024 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1680. Min Act: -0.0001

Data Index: 423578 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1620. Min Act: -0.0001

Data Index: 221388 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1602. Min Act: -0.0001

Data Index: 364536 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1628. Min Act: -0.0001

Data Index: 483177 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1742. Min Act: -0.0001

Data Index: 438568 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1208037 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1535. Min Act: -0.0001

Data Index: 112808 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1130576 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1591. Min Act: -0.0001

Data Index: 945867 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1523. Min Act: -0.0001

Data Index: 438282 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1565. Min Act: -0.0001

Data Index: 825966 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1151366 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1627. Min Act: -0.0001

Data Index: 242133 (C4 (Web Text))

Max Activating Token Index: 505