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

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

Neuron 2544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1366. Min Act: -0.0002

Data Index: 951640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1230. Min Act: -0.0002

Data Index: 922614 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1185. Min Act: -0.0002

Data Index: 901592 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1103. Min Act: -0.0002

Data Index: 518422 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1119. Min Act: -0.0002

Data Index: 873120 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1058. Min Act: -0.0002

Data Index: 756834 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1068. Min Act: -0.0002

Data Index: 770815 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1017. Min Act: -0.0002

Data Index: 855515 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1223827 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1034. Min Act: -0.0002

Data Index: 526806 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1194. Min Act: -0.0002

Data Index: 915612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1637360 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1615914 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1541656 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1011. Min Act: -0.0002

Data Index: 796062 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0798. Min Act: -0.0002

Data Index: 450200 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1046. Min Act: -0.0002

Data Index: 715216 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1043704 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1442308 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 0.1366. Min Range: -0.1366

Max Act: 0.0858. Min Act: -0.0002

Data Index: 683258 (C4 (Web Text))

Max Activating Token Index: 547