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

Dataset: The Pile

Neuron 1469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7143. Min Act: -0.0000

Data Index: 1617104 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1997766 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1660599 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4938. Min Act: -0.0000

Data Index: 886037 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1403395 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1238729 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3777. Min Act: -0.0000

Data Index: 732447 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1423354 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.3306. Min Act: -0.0000

Data Index: 819055 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1344465 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4004. Min Act: -0.0000

Data Index: 397586 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2341. Min Act: -0.0000

Data Index: 971360 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1219735 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1110123 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1618475 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2065. Min Act: -0.0000

Data Index: 575051 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2053. Min Act: -0.0000

Data Index: 707168 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1640368 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1338768 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 1.7843. Min Range: -1.7843

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1779996 (The Pile)

Max Activating Token Index: 348