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

Dataset: The Pile

Neuron 4795 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0000

Data Index: 518021 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6692. Min Act: -0.0000

Data Index: 843373 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5756. Min Act: -0.0000

Data Index: 592986 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1460749 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6096. Min Act: -0.0000

Data Index: 393846 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6033. Min Act: -0.0000

Data Index: 50897 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5457. Min Act: -0.0000

Data Index: 775284 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5734. Min Act: -0.0000

Data Index: 808771 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5274. Min Act: -0.0000

Data Index: 474306 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1678137 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1650129 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1983386 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5344. Min Act: -0.0000

Data Index: 817031 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1943554 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4982. Min Act: -0.0000

Data Index: 312664 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5122. Min Act: -0.0000

Data Index: 587534 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5039. Min Act: -0.0000

Data Index: 414633 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4788. Min Act: -0.0000

Data Index: 642721 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5238. Min Act: -0.0000

Data Index: 691831 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5230. Min Act: -0.0000

Data Index: 296384 (The Pile)

Max Activating Token Index: 1023