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

Dataset: The Pile

Neuron 550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6863. Min Act: -0.0000

Data Index: 524709 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1686528 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6505. Min Act: -0.0000

Data Index: 650397 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6626. Min Act: -0.0000

Data Index: 203000 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1369625 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1956228 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1451858 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1718941 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6014. Min Act: -0.0000

Data Index: 665070 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6054. Min Act: -0.0000

Data Index: 253027 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1976156 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6171. Min Act: -0.0000

Data Index: 919525 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1799880 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1323771 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6077. Min Act: -0.0000

Data Index: 372512 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1627346 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1580897 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1146884 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6030. Min Act: -0.0000

Data Index: 488014 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5976. Min Act: -0.0000

Data Index: 938133 (The Pile)

Max Activating Token Index: 927