Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1266087 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 675127 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1976901 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1410466 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6230. Min Act: -0.0000

Data Index: 753011 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6067. Min Act: -0.0000

Data Index: 468162 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1917160 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4815. Min Act: -0.0000

Data Index: 962401 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1595087 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1438176 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4863. Min Act: -0.0000

Data Index: 230969 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1727728 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5062. Min Act: -0.0000

Data Index: 847957 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1842285 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.3588. Min Act: -0.0000

Data Index: 603655 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1655916 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1948373 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1185488 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5021. Min Act: -0.0000

Data Index: 768207 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1572182 (The Pile)

Max Activating Token Index: 101