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

Dataset: The Pile

Neuron 1853 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: 1.9119. Min Range: -1.9119

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1855830 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1673748 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1015755 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1675980 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.7828. Min Act: -0.0000

Data Index: 1008284 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.5774. Min Act: -0.0000

Data Index: 291268 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.7136. Min Act: -0.0000

Data Index: 248200 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4674. Min Act: -0.0000

Data Index: 860239 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1333998 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1293862 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.5984. Min Act: -0.0000

Data Index: 580706 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1639476 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4707. Min Act: -0.0000

Data Index: 499569 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.3451. Min Act: -0.0000

Data Index: 761985 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4690. Min Act: -0.0000

Data Index: 426896 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4977. Min Act: -0.0000

Data Index: 1598942 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4518. Min Act: -0.0000

Data Index: 6285 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4510. Min Act: -0.0000

Data Index: 96534 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.4472. Min Act: -0.0000

Data Index: 658771 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.9119. Min Range: -1.9119

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1810215 (The Pile)

Max Activating Token Index: 467