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

Dataset: The Pile

Neuron 128 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5682. Min Act: -0.0000

Data Index: 331926 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1602170 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1615482 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1511029 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1911506 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5188. Min Act: -0.0000

Data Index: 293125 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1108286 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1638247 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1242726 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4726. Min Act: -0.0000

Data Index: 733024 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1001808 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1798075 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1528307 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4766. Min Act: -0.0000

Data Index: 181195 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1760216 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4981. Min Act: -0.0000

Data Index: 80925 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4929. Min Act: -0.0000

Data Index: 460796 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1397985 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1968788 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1507630 (The Pile)

Max Activating Token Index: 553