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

Dataset: The Pile

Neuron 1679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1018437 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1943618 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1226737 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1675. Min Act: -0.0000

Data Index: 947161 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1576. Min Act: -0.0000

Data Index: 718134 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1076311 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1298. Min Act: -0.0000

Data Index: 474005 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1538. Min Act: -0.0000

Data Index: 220921 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1313122 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1455775 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1443. Min Act: -0.0000

Data Index: 739526 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1257873 (The Pile)

Max Activating Token Index: 803

Text #12

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1510161 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1328. Min Act: -0.0000

Data Index: 834911 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1009543 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1386815 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1619644 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1376. Min Act: -0.0000

Data Index: 415409 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1483. Min Act: -0.0000

Data Index: 267290 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1492694 (The Pile)

Max Activating Token Index: 742