Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.7046. Min Act: -0.0000

Data Index: 293214 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.9860. Min Act: -0.0000

Data Index: 1557004 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.9113. Min Act: -0.0000

Data Index: 242958 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.7162. Min Act: -0.0000

Data Index: 728023 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.5755. Min Act: -0.0000

Data Index: 1997207 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.5705. Min Act: -0.0000

Data Index: 1421430 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.3597. Min Act: -0.0000

Data Index: 987659 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.6655. Min Act: -0.0000

Data Index: 1196937 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.6633. Min Act: -0.0000

Data Index: 1735703 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.7952. Min Act: -0.0000

Data Index: 828033 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.3304. Min Act: -0.0000

Data Index: 1058044 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.5079. Min Act: -0.0000

Data Index: 1091078 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.7307. Min Act: -0.0000

Data Index: 829191 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.4287. Min Act: -0.0000

Data Index: 104812 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1036771 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2442. Min Act: -0.0000

Data Index: 310914 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.4904. Min Act: -0.0000

Data Index: 373702 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.4577. Min Act: -0.0000

Data Index: 1895679 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.6055. Min Act: -0.0000

Data Index: 383567 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.4483. Min Act: -0.0000

Data Index: 112066 (The Pile)

Max Activating Token Index: 449