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

Dataset: The Pile

Neuron 3743 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: 3.7032. Min Range: -3.7032

Max Act: 3.7032. Min Act: -0.0000

Data Index: 1855109 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1272088 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.8828. Min Act: -0.0000

Data Index: 657909 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.8636. Min Act: -0.0000

Data Index: 179156 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.7170. Min Act: -0.0000

Data Index: 1960978 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.8315. Min Act: -0.0000

Data Index: 1698580 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.7491. Min Act: -0.0000

Data Index: 737948 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.7270. Min Act: -0.0000

Data Index: 1413209 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.7390. Min Act: -0.0000

Data Index: 951247 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.6899. Min Act: -0.0000

Data Index: 225911 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.5936. Min Act: -0.0000

Data Index: 1925201 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.6140. Min Act: -0.0000

Data Index: 1865412 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.5928. Min Act: -0.0000

Data Index: 962542 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.5749. Min Act: -0.0000

Data Index: 867490 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.2770. Min Act: -0.0000

Data Index: 350290 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.3994. Min Act: -0.0000

Data Index: 1983141 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.5120. Min Act: -0.0000

Data Index: 1668527 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.3664. Min Act: -0.0000

Data Index: 982782 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.4879. Min Act: -0.0000

Data Index: 1207433 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 3.7032. Min Range: -3.7032

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1882115 (The Pile)

Max Activating Token Index: 179