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

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

Neuron 1299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3383. Min Range: -4.3383

Max Act: 4.3383. Min Act: -0.0000

Data Index: 289093 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.9594. Min Act: -0.0000

Data Index: 1591951 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 4.3383. Min Range: -4.3383

Max Act: 4.1521. Min Act: -0.0000

Data Index: 839232 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.6833. Min Act: -0.0000

Data Index: 1374361 (Python Code)

Max Activating Token Index: 991

Text #4

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.5567. Min Act: -0.0000

Data Index: 1557226 (Python Code)

Max Activating Token Index: 967

Text #5

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.5206. Min Act: -0.0000

Data Index: 1637711 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.6451. Min Act: -0.0000

Data Index: 934027 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.4579. Min Act: -0.0000

Data Index: 1502734 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.6588. Min Act: -0.0000

Data Index: 1547166 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.5932. Min Act: -0.0000

Data Index: 1462751 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.5973. Min Act: -0.0000

Data Index: 1625292 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3895. Min Act: -0.0000

Data Index: 1579442 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3952. Min Act: -0.0000

Data Index: 1395422 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3716. Min Act: -0.0000

Data Index: 1515539 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.5670. Min Act: -0.0000

Data Index: 1655263 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3902. Min Act: -0.0000

Data Index: 1383774 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3712. Min Act: -0.0000

Data Index: 1517166 (Python Code)

Max Activating Token Index: 476

Text #17

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3612. Min Act: -0.0000

Data Index: 1652268 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3604. Min Act: -0.0000

Data Index: 1560134 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 4.3383. Min Range: -4.3383

Max Act: 3.3633. Min Act: -0.0000

Data Index: 1403536 (Python Code)

Max Activating Token Index: 973