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

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

Neuron 4923 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1395022 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1384388 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1361026 (Python Code)

Max Activating Token Index: 989

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1267. Min Act: -0.0000

Data Index: 691199 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1435514 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1037180 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1206. Min Act: 0.0001

Data Index: 842458 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1139. Min Act: 0.0000

Data Index: 942723 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1097. Min Act: -0.0000

Data Index: 664489 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1256. Min Act: -0.0000

Data Index: 161531 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1113. Min Act: 0.0001

Data Index: 947090 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1589285 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1024. Min Act: 0.0001

Data Index: 946696 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1580697 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1409640 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1110041 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1046. Min Act: -0.0000

Data Index: 269860 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1014. Min Act: 0.0001

Data Index: 802962 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0996. Min Act: 0.0001

Data Index: 897659 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0991. Min Act: 0.0000

Data Index: 89088 (C4 (Web Text))

Max Activating Token Index: 1007