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

Dataset: The Pile

Neuron 846 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.3157. Min Act: -0.0000

Data Index: 1092943 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 5.3157. Min Range: -5.3157

Max Act: 4.9155. Min Act: -0.0000

Data Index: 787282 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 5.3157. Min Range: -5.3157

Max Act: 4.5392. Min Act: -0.0000

Data Index: 1436020 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 5.3157. Min Range: -5.3157

Max Act: 4.5565. Min Act: -0.0000

Data Index: 1128015 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.8778. Min Act: -0.0000

Data Index: 1190771 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.8268. Min Act: -0.0000

Data Index: 1733178 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.9296. Min Act: -0.0000

Data Index: 554461 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.4624. Min Act: -0.0000

Data Index: 1722120 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.6009. Min Act: -0.0000

Data Index: 776332 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.4458. Min Act: -0.0000

Data Index: 1880496 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.5106. Min Act: -0.0000

Data Index: 747074 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.3465. Min Act: -0.0000

Data Index: 1705271 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.5302. Min Act: -0.0000

Data Index: 945887 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.2056. Min Act: -0.0000

Data Index: 752639 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.1188. Min Act: -0.0000

Data Index: 664783 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.1178. Min Act: -0.0000

Data Index: 611631 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.2135. Min Act: -0.0000

Data Index: 1263322 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.0788. Min Act: -0.0000

Data Index: 1477154 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.0307. Min Act: -0.0000

Data Index: 116671 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 5.3157. Min Range: -5.3157

Max Act: 3.0907. Min Act: -0.0000

Data Index: 918635 (The Pile)

Max Activating Token Index: 869