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

Dataset: The Pile

Neuron 825 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: 1.4411. Min Range: -1.4411

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1605252 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4287. Min Act: -0.0000

Data Index: 349359 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1775 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1642673 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1028757 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1402246 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3470. Min Act: -0.0000

Data Index: 1605901 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3656. Min Act: -0.0000

Data Index: 876536 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2261. Min Act: -0.0000

Data Index: 819969 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1849. Min Act: -0.0000

Data Index: 749024 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1866. Min Act: -0.0000

Data Index: 371366 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3140. Min Act: -0.0000

Data Index: 41206 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0953. Min Act: -0.0000

Data Index: 426749 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2035. Min Act: -0.0000

Data Index: 920 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2055. Min Act: -0.0000

Data Index: 306074 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1258. Min Act: -0.0000

Data Index: 680227 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1675559 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0939. Min Act: -0.0000

Data Index: 591753 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1342030 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1474990 (The Pile)

Max Activating Token Index: 819