Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1082256 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1880. Min Act: -0.0001

Data Index: 87252 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1823. Min Act: -0.0001

Data Index: 380625 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1663. Min Act: -0.0001

Data Index: 449865 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1552. Min Act: -0.0001

Data Index: 378593 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1603. Min Act: -0.0001

Data Index: 913145 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1204547 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1257939 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1594. Min Act: -0.0001

Data Index: 406798 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1053201 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1344637 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1477. Min Act: -0.0001

Data Index: 21250 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1479. Min Act: -0.0001

Data Index: 17578 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1445. Min Act: -0.0001

Data Index: 915175 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1314. Min Act: -0.0001

Data Index: 389275 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1422. Min Act: -0.0001

Data Index: 625536 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1077758 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1474. Min Act: -0.0001

Data Index: 129087 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1466. Min Act: -0.0001

Data Index: 873115 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1167805 (C4 (Web Text))

Max Activating Token Index: 71