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

Dataset: The Pile

Neuron 2446 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: 1.2160. Min Range: -1.2160

Max Act: 1.1756. Min Act: -0.0000

Data Index: 293446 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.2123. Min Act: -0.0000

Data Index: 166192 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1050572 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0957. Min Act: -0.0000

Data Index: 754549 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.1501. Min Act: -0.0000

Data Index: 924211 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.1010. Min Act: -0.0000

Data Index: 920483 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1446900 (The Pile)

Max Activating Token Index: 746

Text #7

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1524298 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1229271 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9217. Min Act: -0.0000

Data Index: 470406 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.2160. Min Range: -1.2160

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1915513 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1310519 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9933. Min Act: -0.0000

Data Index: 924172 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9048. Min Act: -0.0000

Data Index: 996050 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8987. Min Act: -0.0000

Data Index: 792700 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1729331 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8215. Min Act: 0.0000

Data Index: 1568366 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8075. Min Act: -0.0000

Data Index: 782045 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1710990 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 1.2160. Min Range: -1.2160

Max Act: 0.9167. Min Act: -0.0000

Data Index: 927909 (The Pile)

Max Activating Token Index: 371