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

Dataset: The Pile

Neuron 276 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.5079. Min Act: -0.0000

Data Index: 416464 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3942. Min Act: -0.0000

Data Index: 545368 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4626. Min Act: -0.0000

Data Index: 664812 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1402154 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1438807 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4816. Min Act: -0.0000

Data Index: 172309 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1667015 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1090522 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4161. Min Act: -0.0000

Data Index: 782232 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1494993 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3945. Min Act: -0.0000

Data Index: 890996 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4513. Min Act: -0.0000

Data Index: 434177 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1655135 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4062. Min Act: -0.0000

Data Index: 293570 (The Pile)

Max Activating Token Index: 956

Text #14

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1237486 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4219. Min Act: -0.0000

Data Index: 222854 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3941. Min Act: -0.0000

Data Index: 118212 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4265. Min Act: -0.0000

Data Index: 217705 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3667. Min Act: -0.0000

Data Index: 721286 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1983748 (The Pile)

Max Activating Token Index: 439