Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1391274 (Python Code)

Max Activating Token Index: 585

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1372745 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1646829 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1478415 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1533841 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1389735 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1573208 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1369667 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1503488 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0996. Min Act: -0.0001

Data Index: 320424 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1500230 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1444442 (Python Code)

Max Activating Token Index: 619

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1548318 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1448558 (Python Code)

Max Activating Token Index: 833

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1646449 (Python Code)

Max Activating Token Index: 266

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1648286 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0989. Min Act: -0.0001

Data Index: 896541 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0997. Min Act: -0.0001

Data Index: 478367 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1587189 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1600408 (Python Code)

Max Activating Token Index: 129