Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1854869 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1302381 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1151918 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4931. Min Act: -0.0000

Data Index: 372481 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5179. Min Act: 0.0000

Data Index: 372530 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5062. Min Act: 0.0000

Data Index: 990640 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1238276 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1658989 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5612. Min Act: -0.0000

Data Index: 187708 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1563932 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4480. Min Act: -0.0000

Data Index: 951288 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1582406 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4384. Min Act: 0.0000

Data Index: 1376761 (The Pile)

Max Activating Token Index: 384

Text #13

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4454. Min Act: 0.0001

Data Index: 156952 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4657. Min Act: 0.0002

Data Index: 1538592 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4280. Min Act: 0.0000

Data Index: 1406704 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1624223 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1496126 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1939180 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1438424 (The Pile)

Max Activating Token Index: 643