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

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

Neuron 2231 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1561580 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1468332 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1385094 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1650047 (Python Code)

Max Activating Token Index: 917

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1516141 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1494886 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1412166 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1446190 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1512776 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1543674 (Python Code)

Max Activating Token Index: 684

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1509264 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1411314 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1603456 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1626725 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1465871 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1597714 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1569209 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1455473 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1480074 (Python Code)

Max Activating Token Index: 554

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1649458 (Python Code)

Max Activating Token Index: 301