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

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

Neuron 1962 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1032995 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1097829 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1898. Min Act: -0.0000

Data Index: 86709 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1149814 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1732. Min Act: -0.0000

Data Index: 160487 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1755. Min Act: -0.0000

Data Index: 936851 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1195864 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1500. Min Act: -0.0000

Data Index: 780610 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1773. Min Act: -0.0000

Data Index: 589544 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1578. Min Act: -0.0000

Data Index: 848811 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1643. Min Act: -0.0000

Data Index: 487036 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1756. Min Act: -0.0000

Data Index: 163556 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1538. Min Act: -0.0000

Data Index: 265969 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1761. Min Act: -0.0000

Data Index: 529861 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1571. Min Act: -0.0000

Data Index: 289723 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1631. Min Act: -0.0000

Data Index: 172295 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1732. Min Act: -0.0000

Data Index: 304174 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1335616 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1075026 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1541. Min Act: -0.0000

Data Index: 575851 (C4 (Web Text))

Max Activating Token Index: 905