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

Dataset: The Pile

Neuron 2400 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: 1.0452. Min Range: -1.0452

Max Act: 1.0452. Min Act: -0.0000

Data Index: 686108 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1161030 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1851223 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7060. Min Act: -0.0000

Data Index: 542899 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1103360 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6749. Min Act: -0.0000

Data Index: 294761 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1372166 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6367. Min Act: -0.0000

Data Index: 149429 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6162. Min Act: -0.0000

Data Index: 914752 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1608365 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1196579 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.6186. Min Act: -0.0000

Data Index: 911399 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1816490 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1122618 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5403. Min Act: -0.0000

Data Index: 285149 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5419. Min Act: -0.0000

Data Index: 986993 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1154245 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1129903 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5445. Min Act: -0.0000

Data Index: 473191 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1899242 (The Pile)

Max Activating Token Index: 814