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

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

Neuron 5086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1746. Min Act: -0.0000

Data Index: 815223 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1643. Min Act: -0.0000

Data Index: 569386 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1391096 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1348776 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1528069 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1594132 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1627489 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1094. Min Act: -0.0000

Data Index: 230651 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1611056 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1226. Min Act: -0.0000

Data Index: 195053 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1561387 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1234. Min Act: -0.0000

Data Index: 536140 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1168383 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1433345 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1083. Min Act: -0.0000

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1500536 (Python Code)

Max Activating Token Index: 486

Text #16

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1231. Min Act: -0.0000

Data Index: 948880 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1434652 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1365118 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1441987 (Python Code)

Max Activating Token Index: 785