Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.2621. Min Act: -0.0001

Data Index: 25056 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1889. Min Act: -0.0001

Data Index: 1028490 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1853. Min Act: -0.0001

Data Index: 554023 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1593982 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1240. Min Act: -0.0001

Data Index: 1365299 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1583. Min Act: -0.0001

Data Index: 1459490 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1466. Min Act: -0.0001

Data Index: 1548765 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1601975 (Python Code)

Max Activating Token Index: 626

Text #8

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1207. Min Act: -0.0001

Data Index: 307168 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1600930 (Python Code)

Max Activating Token Index: 127

Text #10

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0731. Min Act: -0.0001

Data Index: 1495783 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1056286 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1343. Min Act: -0.0001

Data Index: 1420904 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1082. Min Act: -0.0001

Data Index: 1471259 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1028. Min Act: -0.0001

Data Index: 1526597 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0830. Min Act: -0.0001

Data Index: 1490630 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0223. Min Act: -0.0001

Data Index: 207658 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1597204 (Python Code)

Max Activating Token Index: 763

Text #19

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.9712. Min Act: -0.0001

Data Index: 544102 (C4 (Web Text))

Max Activating Token Index: 375