Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1283 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1149529 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1233236 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0698. Min Act: -0.0003

Data Index: 62694 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1267563 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0678. Min Act: -0.0003

Data Index: 34339 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0653. Min Act: -0.0003

Data Index: 734592 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1109057 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0638. Min Act: -0.0003

Data Index: 982625 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1767 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0647. Min Act: -0.0002

Data Index: 763494 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1236929 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1084942 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0643. Min Act: -0.0003

Data Index: 260282 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0603. Min Act: -0.0003

Data Index: 669788 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0609. Min Act: -0.0003

Data Index: 842313 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1219111 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0600. Min Act: -0.0003

Data Index: 374786 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0608. Min Act: -0.0003

Data Index: 512780 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1130944 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1412408 (Python Code)

Max Activating Token Index: 727