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

Dataset: The Pile

Neuron 4771 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: 5.0768. Min Range: -5.0768

Max Act: 5.0768. Min Act: -0.0000

Data Index: 342899 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.5978. Min Act: -0.0000

Data Index: 746423 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.9089. Min Act: -0.0000

Data Index: 1183890 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.5459. Min Act: -0.0000

Data Index: 1049837 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.9118. Min Act: -0.0000

Data Index: 1007426 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.3641. Min Act: -0.0000

Data Index: 1403193 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.6937. Min Act: -0.0000

Data Index: 1151393 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 5.0768. Min Range: -5.0768

Max Act: 3.5387. Min Act: -0.0000

Data Index: 508410 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.4067. Min Act: -0.0000

Data Index: 1942256 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.1877. Min Act: -0.0000

Data Index: 293315 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.7521. Min Act: -0.0000

Data Index: 1164767 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 5.0768. Min Range: -5.0768

Max Act: 3.9851. Min Act: -0.0000

Data Index: 189231 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.0186. Min Act: -0.0000

Data Index: 1501235 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.7408. Min Act: -0.0000

Data Index: 1572949 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.5039. Min Act: -0.0000

Data Index: 1840746 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.4707. Min Act: -0.0000

Data Index: 218278 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.4842. Min Act: -0.0000

Data Index: 697554 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.0837. Min Act: -0.0000

Data Index: 1200433 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 5.0768. Min Range: -5.0768

Max Act: 4.5909. Min Act: -0.0000

Data Index: 1863829 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 5.0768. Min Range: -5.0768

Max Act: 3.8476. Min Act: -0.0000

Data Index: 1212842 (The Pile)

Max Activating Token Index: 856