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

Dataset: The Pile

Neuron 1425 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1834477 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1234447 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1223972 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1782842 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4680. Min Act: -0.0000

Data Index: 212456 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4918. Min Act: -0.0000

Data Index: 997614 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1135817 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4453. Min Act: -0.0000

Data Index: 394503 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4431. Min Act: -0.0000

Data Index: 60785 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1979121 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4433. Min Act: -0.0000

Data Index: 452236 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4399. Min Act: -0.0000

Data Index: 967676 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4557. Min Act: -0.0000

Data Index: 817857 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1215468 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1053824 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4330. Min Act: -0.0000

Data Index: 724534 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4147. Min Act: -0.0000

Data Index: 39081 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1249763 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1307757 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4513. Min Act: -0.0000

Data Index: 492156 (The Pile)

Max Activating Token Index: 134