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

Dataset: The Pile

Neuron 4065 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: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0000

Data Index: 37583 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1408. Min Act: -0.0000

Data Index: 160642 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1454324 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1327. Min Act: -0.0000

Data Index: 729538 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1229. Min Act: -0.0000

Data Index: 934318 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1285259 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1116. Min Act: 0.0000

Data Index: 544547 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1116. Min Act: -0.0000

Data Index: 398952 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1172. Min Act: -0.0000

Data Index: 35966 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1053379 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1088. Min Act: 0.0000

Data Index: 1466147 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1092. Min Act: -0.0000

Data Index: 550316 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1784104 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1800324 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1510850 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1862680 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0886. Min Act: -0.0000

Data Index: 584597 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1341102 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1462721 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0886. Min Act: -0.0000

Data Index: 616055 (The Pile)

Max Activating Token Index: 275