Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1801. Min Act: -0.0001

Data Index: 429228 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1735. Min Act: -0.0001

Data Index: 976727 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1931. Min Act: -0.0001

Data Index: 996917 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1738. Min Act: -0.0001

Data Index: 778957 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1716. Min Act: -0.0001

Data Index: 373257 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1522. Min Act: -0.0001

Data Index: 702736 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1603. Min Act: -0.0001

Data Index: 605161 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1508. Min Act: -0.0001

Data Index: 844355 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1474. Min Act: -0.0001

Data Index: 517581 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1333945 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1215404 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1388. Min Act: -0.0001

Data Index: 533794 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1444. Min Act: -0.0001

Data Index: 969488 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1257475 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1309186 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1483. Min Act: -0.0001

Data Index: 120715 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1571. Min Act: -0.0001

Data Index: 645301 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1319. Min Act: -0.0001

Data Index: 973345 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1383. Min Act: -0.0001

Data Index: 602115 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1506. Min Act: -0.0001

Data Index: 983225 (C4 (Web Text))

Max Activating Token Index: 30