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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0213. Min Act: -0.0001

Data Index: 165225 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0001

Data Index: 467519 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1211357 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0135. Min Act: -0.0001

Data Index: 954920 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0134. Min Act: -0.0001

Data Index: 989545 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1187396 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0123. Min Act: -0.0001

Data Index: 690258 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1238944 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0118. Min Act: -0.0001

Data Index: 1092940 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0109. Min Act: -0.0001

Data Index: 771982 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0107. Min Act: -0.0001

Data Index: 766761 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0108. Min Act: -0.0001

Data Index: 809879 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0106. Min Act: -0.0001

Data Index: 1356721 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0106. Min Act: -0.0001

Data Index: 602578 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0102. Min Act: -0.0001

Data Index: 582932 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0098. Min Act: -0.0001

Data Index: 1440476 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0095. Min Act: -0.0001

Data Index: 4063 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0100. Min Act: -0.0001

Data Index: 1060820 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0096. Min Act: -0.0001

Data Index: 1286048 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0102. Min Act: -0.0001

Data Index: 368013 (C4 (Web Text))

Max Activating Token Index: 123