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

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

Neuron 2495 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: 0.9519. Min Range: -0.9519

Max Act: 0.9519. Min Act: -0.0001

Data Index: 977462 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7457. Min Act: -0.0001

Data Index: 549027 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7105. Min Act: -0.0001

Data Index: 1124433 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6589. Min Act: -0.0001

Data Index: 528758 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6571. Min Act: -0.0001

Data Index: 1060568 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7058. Min Act: -0.0001

Data Index: 58716 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1211587 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1043948 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6427. Min Act: -0.0001

Data Index: 43347 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6527. Min Act: -0.0001

Data Index: 470095 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5977. Min Act: -0.0001

Data Index: 213095 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6247. Min Act: -0.0001

Data Index: 152833 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6453. Min Act: -0.0001

Data Index: 106846 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5667. Min Act: -0.0001

Data Index: 1282867 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6746. Min Act: -0.0001

Data Index: 455168 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6213. Min Act: -0.0001

Data Index: 540035 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6176. Min Act: -0.0001

Data Index: 868098 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6009. Min Act: -0.0001

Data Index: 1266039 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1128391 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1193350 (C4 (Web Text))

Max Activating Token Index: 57