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

Dataset: The Pile

Neuron 3438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.4335. Min Act: -0.0000

Data Index: 177461 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.6181. Min Act: -0.0000

Data Index: 1713287 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1762512 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.3344. Min Act: -0.0000

Data Index: 707256 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1477364 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1850931 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.6181. Min Range: -1.6181

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1155159 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.9841. Min Act: -0.0000

Data Index: 351166 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1053569 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8977. Min Act: -0.0000

Data Index: 419475 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8665. Min Act: -0.0000

Data Index: 70226 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1625751 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8679. Min Act: -0.0000

Data Index: 810512 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1441201 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.7277. Min Act: -0.0000

Data Index: 882401 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.8126. Min Act: -0.0000

Data Index: 409469 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.7311. Min Act: -0.0000

Data Index: 302523 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1227257 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1251040 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.6181. Min Range: -1.6181

Max Act: 0.7377. Min Act: -0.0000

Data Index: 831241 (The Pile)

Max Activating Token Index: 676