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

Dataset: The Pile

Neuron 2308 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: 1.5161. Min Range: -1.5161

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1050586 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.4290. Min Act: -0.0000

Data Index: 207949 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1177007 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.2808. Min Act: 0.0000

Data Index: 171141 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1540374 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0777. Min Act: -0.0000

Data Index: 831180 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9106. Min Act: 0.0000

Data Index: 273931 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9360. Min Act: -0.0000

Data Index: 570871 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1193406 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8444. Min Act: -0.0000

Data Index: 924946 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1246897 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1031929 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8788. Min Act: -0.0000

Data Index: 838906 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8170. Min Act: -0.0000

Data Index: 649333 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8065. Min Act: -0.0000

Data Index: 308828 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1502049 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8456. Min Act: -0.0000

Data Index: 470450 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1068361 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8194. Min Act: -0.0000

Data Index: 691026 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8192. Min Act: -0.0000

Data Index: 860513 (The Pile)

Max Activating Token Index: 309