Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1639280 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1378. Min Act: -0.0000

Data Index: 972152 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1471137 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1306. Min Act: -0.0001

Data Index: 955637 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1551692 (Python Code)

Max Activating Token Index: 508

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1402062 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1127061 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1336006 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1497084 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1541208 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1066089 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1285404 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1076. Min Act: -0.0000

Data Index: 638018 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1058. Min Act: -0.0000

Data Index: 265149 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1489791 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1123697 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.0981. Min Act: -0.0001

Data Index: 310116 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1081. Min Act: -0.0001

Data Index: 403734 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1004. Min Act: -0.0001

Data Index: 431253 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1600496 (Python Code)

Max Activating Token Index: 493