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

Dataset: The Pile

Neuron 1896 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: 1.4838. Min Range: -1.4838

Max Act: 1.4838. Min Act: -0.0000

Data Index: 410576 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4178. Min Act: -0.0000

Data Index: 789203 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4639. Min Act: -0.0000

Data Index: 696323 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2783. Min Act: -0.0000

Data Index: 595363 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1196896 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2372. Min Act: -0.0000

Data Index: 810612 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2668. Min Act: -0.0000

Data Index: 750482 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2238. Min Act: -0.0000

Data Index: 303659 (The Pile)

Max Activating Token Index: 374

Text #8

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1691. Min Act: -0.0000

Data Index: 237724 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2385. Min Act: -0.0000

Data Index: 821670 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1771560 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1732098 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1179251 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 1.4838. Min Range: -1.4838

Max Act: 0.9652. Min Act: -0.0000

Data Index: 444001 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1424173 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1331. Min Act: -0.0000

Data Index: 203870 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1213. Min Act: -0.0000

Data Index: 223092 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1783220 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1399923 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.0984. Min Act: -0.0000

Data Index: 297253 (The Pile)

Max Activating Token Index: 64