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

Dataset: The Pile

Neuron 2508 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8027. Min Act: -0.0000

Data Index: 294025 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1587955 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7585. Min Act: -0.0000

Data Index: 111933 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1146377 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6341. Min Act: -0.0000

Data Index: 488697 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1137822 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1087807 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6737. Min Act: -0.0000

Data Index: 441282 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6448. Min Act: -0.0000

Data Index: 573758 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6590. Min Act: -0.0000

Data Index: 557464 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1000581 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5528. Min Act: -0.0000

Data Index: 792415 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1895961 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1938758 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6156. Min Act: -0.0000

Data Index: 441381 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5538. Min Act: -0.0000

Data Index: 434936 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4860. Min Act: -0.0000

Data Index: 296836 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5096. Min Act: -0.0000

Data Index: 331760 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5768. Min Act: -0.0000

Data Index: 540414 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5658. Min Act: -0.0000

Data Index: 368285 (The Pile)

Max Activating Token Index: 276