Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5746 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1198923 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0767. Min Act: -0.0001

Data Index: 102588 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0731. Min Act: -0.0001

Data Index: 964470 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1089497 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0693. Min Act: -0.0001

Data Index: 584423 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0606. Min Act: -0.0001

Data Index: 978348 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0623. Min Act: -0.0001

Data Index: 410298 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0615. Min Act: -0.0001

Data Index: 283088 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0546. Min Act: -0.0001

Data Index: 881387 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1307310 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0500. Min Act: -0.0001

Data Index: 987980 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0507. Min Act: -0.0001

Data Index: 179900 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0470. Min Act: -0.0001

Data Index: 904502 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0556. Min Act: -0.0001

Data Index: 99131 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0513. Min Act: -0.0001

Data Index: 65887 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0541. Min Act: -0.0001

Data Index: 70993 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1288147 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0492. Min Act: -0.0001

Data Index: 418426 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1139257 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0533. Min Act: -0.0001

Data Index: 404317 (C4 (Web Text))

Max Activating Token Index: 101