Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4933 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0000

Data Index: 866008 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1469704 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1628457 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1454105 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1396912 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1513415 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1383624 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1368117 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1510505 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1438591 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1597771 (Python Code)

Max Activating Token Index: 334

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1062168 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1634010 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1391661 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1198. Min Act: -0.0000

Data Index: 642726 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1618168 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1615134 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1383537 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1136. Min Act: -0.0001

Data Index: 538835 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1429562 (Python Code)

Max Activating Token Index: 724