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

Dataset: The Pile

Neuron 3439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1731059 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1619909 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1829338 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1412127 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1445664 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1250104 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1769380 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9790. Min Act: -0.0000

Data Index: 391760 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1495908 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1935708 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8788. Min Act: -0.0000

Data Index: 786385 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8557. Min Act: -0.0000

Data Index: 686120 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1468257 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8541. Min Act: -0.0000

Data Index: 41703 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8738. Min Act: -0.0000

Data Index: 120080 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8060. Min Act: -0.0000

Data Index: 596726 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1875216 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1766323 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1375598 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1277581 (The Pile)

Max Activating Token Index: 196