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

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

Neuron 4400 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1330287 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3107. Min Act: -0.0000

Data Index: 86054 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2280. Min Act: -0.0000

Data Index: 688864 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1331251 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1701. Min Act: -0.0000

Data Index: 637841 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1850. Min Act: -0.0000

Data Index: 823995 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1910. Min Act: -0.0000

Data Index: 481979 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1543992 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1516902 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1777. Min Act: -0.0000

Data Index: 48222 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1341558 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1573. Min Act: -0.0000

Data Index: 158124 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1572. Min Act: -0.0000

Data Index: 662840 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1560. Min Act: -0.0000

Data Index: 452656 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1560529 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1548. Min Act: -0.0000

Data Index: 51393 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1386988 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1509. Min Act: -0.0000

Data Index: 626531 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1524. Min Act: -0.0000

Data Index: 296920 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1400. Min Act: -0.0000

Data Index: 437707 (C4 (Web Text))

Max Activating Token Index: 561