Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2685. Min Act: -0.0000

Data Index: 729985 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1371687 (Python Code)

Max Activating Token Index: 1005

Text #2

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1613294 (Python Code)

Max Activating Token Index: 751

Text #3

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1838. Min Act: -0.0001

Data Index: 761481 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1059075 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1819. Min Act: -0.0000

Data Index: 626811 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1092379 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1817. Min Act: -0.0000

Data Index: 290233 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1607. Min Act: -0.0000

Data Index: 762105 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1409043 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1639. Min Act: -0.0000

Data Index: 553535 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1154172 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1591. Min Act: -0.0000

Data Index: 89397 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1569. Min Act: -0.0000

Data Index: 360580 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1521. Min Act: -0.0001

Data Index: 363260 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1022644 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1431879 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1419. Min Act: -0.0000

Data Index: 578712 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1374815 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1370. Min Act: -0.0000

Data Index: 284444 (C4 (Web Text))

Max Activating Token Index: 357