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

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

Neuron 762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0000

Data Index: 913235 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1888. Min Act: -0.0000

Data Index: 341580 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1626. Min Act: -0.0000

Data Index: 198989 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1563. Min Act: -0.0000

Data Index: 335275 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1649. Min Act: -0.0000

Data Index: 156564 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1520. Min Act: -0.0000

Data Index: 754605 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1077841 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1561. Min Act: -0.0000

Data Index: 857051 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1278339 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1439. Min Act: -0.0000

Data Index: 128534 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1527. Min Act: -0.0000

Data Index: 967020 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1006646 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1304560 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1262756 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1533. Min Act: -0.0000

Data Index: 481233 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1417. Min Act: -0.0000

Data Index: 591678 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1476. Min Act: -0.0000

Data Index: 579901 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1242021 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1121144 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1525. Min Act: -0.0000

Data Index: 196024 (C4 (Web Text))

Max Activating Token Index: 919