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

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

Neuron 3841 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1333187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0412. Min Act: -0.0003

Data Index: 293401 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1005452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1149991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1197960 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1200082 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0379. Min Act: -0.0003

Data Index: 963867 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1070979 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0389. Min Act: -0.0003

Data Index: 192472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1078569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0401. Min Act: -0.0003

Data Index: 308072 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0388. Min Act: -0.0003

Data Index: 887026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0379. Min Act: -0.0003

Data Index: 255568 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0363. Min Act: -0.0003

Data Index: 570193 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0372. Min Act: -0.0003

Data Index: 851211 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1117723 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1065729 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0348. Min Act: -0.0003

Data Index: 966965 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0301. Min Act: -0.0003

Data Index: 628478 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0389. Min Act: -0.0003

Data Index: 637980 (C4 (Web Text))

Max Activating Token Index: 1023