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

Dataset: The Pile

Neuron 934 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1889806 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1962. Min Act: -0.0000

Data Index: 661986 (The Pile)

Max Activating Token Index: 909

Text #2

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1253586 (The Pile)

Max Activating Token Index: 518

Text #3

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1879. Min Act: -0.0000

Data Index: 794082 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1755748 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1800. Min Act: -0.0000

Data Index: 417264 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1625. Min Act: -0.0000

Data Index: 999843 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1545. Min Act: -0.0000

Data Index: 552279 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1596. Min Act: -0.0000

Data Index: 635954 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1411. Min Act: 0.0000

Data Index: 1203813 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1427. Min Act: -0.0000

Data Index: 630700 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1468573 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1420. Min Act: -0.0000

Data Index: 715822 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1409. Min Act: -0.0000

Data Index: 694962 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1350. Min Act: -0.0000

Data Index: 752578 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1274. Min Act: -0.0000

Data Index: 18825 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1513822 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1458666 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1362. Min Act: -0.0000

Data Index: 881908 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1299. Min Act: -0.0000

Data Index: 494031 (The Pile)

Max Activating Token Index: 947