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

Dataset: The Pile

Neuron 3495 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: 1.2152. Min Range: -1.2152

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1422082 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1848675 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1509158 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9545. Min Act: -0.0000

Data Index: 862477 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9637. Min Act: -0.0000

Data Index: 710789 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1213920 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1108417 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8823. Min Act: -0.0000

Data Index: 326313 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1174473 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1449855 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1093891 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8805. Min Act: -0.0000

Data Index: 405071 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8599. Min Act: -0.0000

Data Index: 774390 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8558. Min Act: -0.0000

Data Index: 157000 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8489. Min Act: -0.0000

Data Index: 367473 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8614. Min Act: -0.0000

Data Index: 457342 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1274955 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8675. Min Act: -0.0000

Data Index: 797929 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8155. Min Act: -0.0000

Data Index: 967228 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1964764 (The Pile)

Max Activating Token Index: 875