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

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

Neuron 2342 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1290. Min Act: -0.0002

Data Index: 794095 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0002

Data Index: 244464 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1207. Min Act: -0.0002

Data Index: 680612 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1199. Min Act: -0.0002

Data Index: 104773 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1032540 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1228543 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1217. Min Act: -0.0002

Data Index: 568342 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1194526 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1175. Min Act: -0.0001

Data Index: 532135 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1064. Min Act: -0.0002

Data Index: 450701 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1202. Min Act: -0.0002

Data Index: 900068 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1318807 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1299574 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1110. Min Act: -0.0001

Data Index: 303471 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1034. Min Act: -0.0002

Data Index: 446140 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1071486 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0996. Min Act: -0.0002

Data Index: 539232 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0938. Min Act: -0.0002

Data Index: 23257 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1009. Min Act: -0.0002

Data Index: 443058 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1057. Min Act: -0.0002

Data Index: 540602 (C4 (Web Text))

Max Activating Token Index: 127