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

Dataset: The Pile

Neuron 2497 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: 0.7656. Min Range: -0.7656

Max Act: 0.7092. Min Act: -0.0000

Data Index: 157061 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7185. Min Act: -0.0000

Data Index: 380610 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7656. Min Act: 0.0000

Data Index: 146350 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1213239 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1079882 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1551826 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6244. Min Act: 0.0000

Data Index: 1771979 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6521. Min Act: -0.0000

Data Index: 638917 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6293. Min Act: 0.0000

Data Index: 1364699 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6655. Min Act: 0.0000

Data Index: 817361 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6458. Min Act: -0.0000

Data Index: 840452 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6436. Min Act: 0.0000

Data Index: 1587137 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6669. Min Act: -0.0000

Data Index: 500529 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6106. Min Act: 0.0000

Data Index: 72109 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1617248 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6322. Min Act: -0.0000

Data Index: 605537 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1519437 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6092. Min Act: -0.0000

Data Index: 497529 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6058. Min Act: -0.0000

Data Index: 572397 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1001188 (The Pile)

Max Activating Token Index: 851