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

Dataset: The Pile

Neuron 785 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: 1.1384. Min Range: -1.1384

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1449094 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 1.1384. Min Range: -1.1384

Max Act: 1.1125. Min Act: -0.0000

Data Index: 626683 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8561. Min Act: -0.0000

Data Index: 294703 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1728371 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 1.1384. Min Range: -1.1384

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1631130 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9920. Min Act: -0.0000

Data Index: 109393 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1503106 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9098. Min Act: -0.0000

Data Index: 471563 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1800599 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8276. Min Act: -0.0000

Data Index: 350804 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7750. Min Act: -0.0000

Data Index: 942457 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8204. Min Act: -0.0000

Data Index: 307005 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7886. Min Act: -0.0000

Data Index: 750792 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1342812 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1080677 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7555. Min Act: -0.0000

Data Index: 78496 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7311. Min Act: -0.0000

Data Index: 720891 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1305872 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.7220. Min Act: -0.0000

Data Index: 482605 (The Pile)

Max Activating Token Index: 943

Text #19

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1722629 (The Pile)

Max Activating Token Index: 589