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

Dataset: The Pile

Neuron 1514 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: 0.1557. Min Range: -0.1557

Max Act: 0.1557. Min Act: -0.0000

Data Index: 585332 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1461. Min Act: -0.0000

Data Index: 40547 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1330. Min Act: -0.0000

Data Index: 98555 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1120. Min Act: -0.0000

Data Index: 164274 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1924205 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1316393 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1118. Min Act: -0.0000

Data Index: 59000 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1333. Min Act: -0.0000

Data Index: 777383 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1169951 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1145. Min Act: -0.0000

Data Index: 231401 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1353247 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1957427 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1080. Min Act: -0.0000

Data Index: 181875 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1340785 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1934807 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1163961 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1853484 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1735899 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1141257 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.1557. Min Range: -0.1557

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1598339 (The Pile)

Max Activating Token Index: 273