Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1825467 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1606615 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1157941 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9143. Min Act: -0.0000

Data Index: 419775 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9181. Min Act: -0.0000

Data Index: 553101 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1258570 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9115. Min Act: -0.0000

Data Index: 832345 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1319301 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8745. Min Act: -0.0000

Data Index: 449211 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8490. Min Act: -0.0000

Data Index: 979436 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8149. Min Act: -0.0000

Data Index: 333783 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7876. Min Act: -0.0000

Data Index: 173595 (The Pile)

Max Activating Token Index: 954

Text #12

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8349. Min Act: -0.0000

Data Index: 405383 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8503. Min Act: -0.0000

Data Index: 251093 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1471860 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8656. Min Act: -0.0000

Data Index: 819189 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1327116 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8071. Min Act: -0.0000

Data Index: 773718 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1241416 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8328. Min Act: -0.0000

Data Index: 727207 (The Pile)

Max Activating Token Index: 236