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

Dataset: The Pile

Neuron 991 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: 0.8463. Min Range: -0.8463

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1828217 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7703. Min Act: -0.0000

Data Index: 623896 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1789125 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1486777 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1886940 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1938227 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1601502 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1298261 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1288590 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1805712 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1229693 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1866019 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4175. Min Act: -0.0000

Data Index: 498958 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4383. Min Act: -0.0000

Data Index: 73465 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.3937. Min Act: -0.0000

Data Index: 698328 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1671596 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1530191 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.3999. Min Act: -0.0000

Data Index: 438301 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1498317 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1069099 (The Pile)

Max Activating Token Index: 919