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

Dataset: The Pile

Neuron 2519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.5773. Min Act: -0.0000

Data Index: 725484 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.3772. Min Act: -0.0000

Data Index: 1510536 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.2791. Min Act: -0.0000

Data Index: 1820227 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1671888 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.8729. Min Act: -0.0000

Data Index: 1415534 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.8073. Min Act: -0.0000

Data Index: 573865 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 3.5773. Min Range: -3.5773

Max Act: 3.0616. Min Act: -0.0000

Data Index: 689733 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.9531. Min Act: -0.0000

Data Index: 1325107 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.8151. Min Act: -0.0000

Data Index: 407787 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.5383. Min Act: -0.0000

Data Index: 1229782 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.6064. Min Act: -0.0000

Data Index: 321943 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.4507. Min Act: -0.0000

Data Index: 112410 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.5909. Min Act: -0.0000

Data Index: 336563 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.4326. Min Act: -0.0000

Data Index: 1081890 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.2953. Min Act: -0.0000

Data Index: 219036 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.4179. Min Act: -0.0000

Data Index: 975450 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.5300. Min Act: -0.0000

Data Index: 1926365 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.2701. Min Act: -0.0000

Data Index: 1547191 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.4767. Min Act: -0.0000

Data Index: 1847799 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 3.5773. Min Range: -3.5773

Max Act: 2.3262. Min Act: -0.0000

Data Index: 362415 (The Pile)

Max Activating Token Index: 427