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

Dataset: The Pile

Neuron 800 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: 1.0135. Min Range: -1.0135

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1271465 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1749303 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1309879 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1122436 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1705426 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1992487 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1138425 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1945858 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7595. Min Act: -0.0000

Data Index: 923807 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1647439 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.5919. Min Act: -0.0000

Data Index: 656979 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1060302 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1640877 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7467. Min Act: 0.0000

Data Index: 450904 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7326. Min Act: -0.0000

Data Index: 690073 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1202897 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7454. Min Act: -0.0000

Data Index: 99230 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.6879. Min Act: -0.0000

Data Index: 733107 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1172260 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 1.0135. Min Range: -1.0135

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1796135 (The Pile)

Max Activating Token Index: 831