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

Dataset: The Pile

Neuron 2297 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: 1.3708. Min Range: -1.3708

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1055484 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1937. Min Act: -0.0000

Data Index: 347911 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1015423 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1559. Min Act: -0.0000

Data Index: 157700 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1170845 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1099234 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0512. Min Act: -0.0000

Data Index: 113372 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0394. Min Act: -0.0000

Data Index: 773860 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0257. Min Act: -0.0000

Data Index: 214285 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9778. Min Act: -0.0000

Data Index: 934937 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1703592 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9158. Min Act: -0.0000

Data Index: 783582 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1566392 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1162177 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8619. Min Act: -0.0000

Data Index: 898066 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9660. Min Act: -0.0000

Data Index: 150100 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8604. Min Act: -0.0000

Data Index: 537883 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8360. Min Act: -0.0000

Data Index: 378564 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1096182 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1538091 (The Pile)

Max Activating Token Index: 668