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

Dataset: The Pile

Neuron 2806 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: 1.6794. Min Range: -1.6794

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1467405 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6543. Min Act: -0.0000

Data Index: 799627 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6794. Min Act: -0.0000

Data Index: 231083 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1136511 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5600. Min Act: -0.0000

Data Index: 252142 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6576. Min Act: -0.0000

Data Index: 910247 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6054. Min Act: -0.0000

Data Index: 770826 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5367. Min Act: -0.0000

Data Index: 277076 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5137. Min Act: -0.0000

Data Index: 39743 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5002. Min Act: -0.0000

Data Index: 202024 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4685. Min Act: -0.0000

Data Index: 988446 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1901164 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1065579 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1379146 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5435. Min Act: -0.0000

Data Index: 929472 (The Pile)

Max Activating Token Index: 931

Text #15

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4478. Min Act: -0.0000

Data Index: 948047 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4508. Min Act: -0.0000

Data Index: 966530 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1976143 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1735407 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1402437 (The Pile)

Max Activating Token Index: 950