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

Dataset: The Pile

Neuron 3828 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: 0.6663. Min Range: -0.6663

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1655025 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1844376 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5755. Min Act: -0.0000

Data Index: 234265 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1178352 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1790515 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5982. Min Act: -0.0000

Data Index: 389703 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1716982 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1690669 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5657. Min Act: -0.0000

Data Index: 332102 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5425. Min Act: -0.0000

Data Index: 568779 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5267. Min Act: -0.0000

Data Index: 557845 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5375. Min Act: -0.0000

Data Index: 951637 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1668263 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1085272 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5204. Min Act: -0.0000

Data Index: 951593 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5675. Min Act: -0.0000

Data Index: 663497 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1701119 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5349. Min Act: -0.0000

Data Index: 320563 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1297650 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5261. Min Act: -0.0000

Data Index: 772985 (The Pile)

Max Activating Token Index: 48