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

Dataset: The Pile

Neuron 1135 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: 1.8745. Min Range: -1.8745

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1184020 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1459533 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.8483. Min Act: -0.0000

Data Index: 585428 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6225. Min Act: -0.0000

Data Index: 233921 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6543. Min Act: -0.0000

Data Index: 1640188 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5973. Min Act: 0.0000

Data Index: 751483 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5062. Min Act: -0.0000

Data Index: 1866987 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6694. Min Act: -0.0000

Data Index: 241409 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6508. Min Act: -0.0000

Data Index: 637763 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1271164 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4888. Min Act: 0.0000

Data Index: 1822629 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4954. Min Act: 0.0000

Data Index: 1573397 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.3961. Min Act: -0.0000

Data Index: 160821 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4241. Min Act: -0.0000

Data Index: 888640 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1486426 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1524948 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1381526 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1120859 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1411411 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1816226 (The Pile)

Max Activating Token Index: 306