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

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

Neuron 3557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1976. Min Act: -0.0001

Data Index: 510257 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1049249 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1840. Min Act: -0.0001

Data Index: 731958 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1635. Min Act: -0.0000

Data Index: 497454 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1636. Min Act: -0.0001

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1251125 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1649. Min Act: -0.0001

Data Index: 968502 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1700. Min Act: -0.0001

Data Index: 111602 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1598. Min Act: -0.0001

Data Index: 166852 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1558. Min Act: -0.0001

Data Index: 497023 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1615. Min Act: -0.0000

Data Index: 90263 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1711. Min Act: -0.0001

Data Index: 901330 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1542. Min Act: -0.0001

Data Index: 191735 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1596. Min Act: -0.0001

Data Index: 219486 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1386895 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1499. Min Act: -0.0001

Data Index: 329445 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1480. Min Act: -0.0001

Data Index: 728919 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1504. Min Act: -0.0000

Data Index: 313328 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1489. Min Act: -0.0000

Data Index: 916297 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1253144 (C4 (Web Text))

Max Activating Token Index: 991