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

Dataset: The Pile

Neuron 3082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7506. Min Act: -0.0000

Data Index: 249680 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7970. Min Act: -0.0000

Data Index: 63085 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1457491 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7222. Min Act: -0.0000

Data Index: 308693 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1756482 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7401. Min Act: -0.0000

Data Index: 444949 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6957. Min Act: -0.0000

Data Index: 13760 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7365. Min Act: -0.0000

Data Index: 362388 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1492535 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1379640 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1830677 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1862709 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6363. Min Act: -0.0000

Data Index: 521397 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6508. Min Act: -0.0000

Data Index: 588266 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6209. Min Act: -0.0000

Data Index: 39833 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5884. Min Act: -0.0000

Data Index: 691960 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5929. Min Act: -0.0000

Data Index: 869937 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5662. Min Act: -0.0000

Data Index: 694976 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1858658 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1063100 (The Pile)

Max Activating Token Index: 425