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

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

Neuron 3724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1639. Min Act: -0.0001

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1625. Min Act: -0.0001

Data Index: 544648 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1871. Min Act: -0.0001

Data Index: 961353 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1497. Min Act: -0.0001

Data Index: 885982 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1603. Min Act: -0.0001

Data Index: 995700 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1506. Min Act: -0.0001

Data Index: 531030 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1549. Min Act: -0.0000

Data Index: 23695 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1083727 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1478. Min Act: -0.0000

Data Index: 653284 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1368. Min Act: -0.0000

Data Index: 682209 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1414. Min Act: -0.0001

Data Index: 62844 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1316. Min Act: -0.0001

Data Index: 241285 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1231316 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1477. Min Act: -0.0001

Data Index: 907665 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1303. Min Act: -0.0001

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1471. Min Act: -0.0000

Data Index: 767025 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1101187 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1396. Min Act: -0.0001

Data Index: 795248 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1392. Min Act: -0.0001

Data Index: 890501 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.1871. Min Range: -0.1871

Max Act: 0.1435. Min Act: -0.0001

Data Index: 421037 (C4 (Web Text))

Max Activating Token Index: 949