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

Dataset: The Pile

Neuron 1590 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: 5.4964. Min Range: -5.4964

Max Act: 5.4161. Min Act: -0.0000

Data Index: 548342 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.4126. Min Act: -0.0000

Data Index: 472949 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.4964. Min Act: -0.0000

Data Index: 1088353 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.0512. Min Act: -0.0000

Data Index: 929217 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.3570. Min Act: -0.0000

Data Index: 1527239 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.0186. Min Act: -0.0000

Data Index: 649343 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.0128. Min Act: -0.0000

Data Index: 614845 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.9469. Min Act: -0.0000

Data Index: 294898 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.8862. Min Act: -0.0000

Data Index: 24811 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.7006. Min Act: -0.0000

Data Index: 1508841 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.6539. Min Act: -0.0000

Data Index: 1629890 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 5.4964. Min Range: -5.4964

Max Act: 5.0102. Min Act: -0.0000

Data Index: 272842 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.8936. Min Act: -0.0000

Data Index: 27225 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.3973. Min Act: -0.0000

Data Index: 1503215 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.3977. Min Act: -0.0000

Data Index: 804086 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.6848. Min Act: -0.0000

Data Index: 760484 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.0858. Min Act: -0.0000

Data Index: 933041 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.4064. Min Act: -0.0000

Data Index: 1365821 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.1729. Min Act: -0.0000

Data Index: 779181 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 5.4964. Min Range: -5.4964

Max Act: 4.3194. Min Act: -0.0000

Data Index: 1729763 (The Pile)

Max Activating Token Index: 541