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

Dataset: The Pile

Neuron 1870 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.1183. Min Act: -0.0000

Data Index: 558407 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.1260. Min Act: -0.0000

Data Index: 853858 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1805303 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0137. Min Act: -0.0000

Data Index: 572630 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0523. Min Act: -0.0000

Data Index: 806821 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0404. Min Act: -0.0000

Data Index: 755135 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9671. Min Act: -0.0000

Data Index: 44894 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0175. Min Act: -0.0000

Data Index: 880251 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9644. Min Act: -0.0000

Data Index: 1848891 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9180. Min Act: -0.0000

Data Index: 271672 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9938. Min Act: -0.0000

Data Index: 538014 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.1260. Min Range: -1.1260

Max Act: 1.0528. Min Act: -0.0000

Data Index: 510989 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1400705 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1439045 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1189565 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9452. Min Act: -0.0000

Data Index: 781630 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1332263 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1384479 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9259. Min Act: -0.0000

Data Index: 309814 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1921944 (The Pile)

Max Activating Token Index: 857