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

Dataset: The Pile

Neuron 850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.9174. Min Act: -0.0000

Data Index: 1746837 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1294064 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1872809 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1345. Min Act: -0.0000

Data Index: 159299 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1215367 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1177984 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1863966 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1234598 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1175647 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1780673 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.0782. Min Act: -0.0000

Data Index: 803745 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1104. Min Act: -0.0000

Data Index: 123457 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1317. Min Act: -0.0000

Data Index: 754587 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 1.9174. Min Range: -1.9174

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1691771 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1526207 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1797074 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1117149 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 1.9174. Min Range: -1.9174

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1423529 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1539190 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 1.9174. Min Range: -1.9174

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1436276 (The Pile)

Max Activating Token Index: 629