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

Dataset: The Pile

Neuron 1708 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: 0.6787. Min Range: -0.6787

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1859786 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.6787. Min Act: -0.0000

Data Index: 529708 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1770029 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5408. Min Act: -0.0000

Data Index: 452117 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1904341 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5289. Min Act: -0.0000

Data Index: 382742 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5816. Min Act: -0.0000

Data Index: 335069 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4183. Min Act: -0.0000

Data Index: 373971 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5060. Min Act: -0.0000

Data Index: 959918 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1506504 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4731. Min Act: -0.0000

Data Index: 95349 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1834856 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4631. Min Act: -0.0000

Data Index: 640277 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1134169 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4344. Min Act: -0.0000

Data Index: 657370 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1160174 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4272. Min Act: -0.0000

Data Index: 912352 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4729. Min Act: -0.0000

Data Index: 775415 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1397029 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4963. Min Act: -0.0000

Data Index: 69085 (The Pile)

Max Activating Token Index: 439