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

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

Neuron 2004 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: 0.1596. Min Range: -0.1596

Max Act: 0.1596. Min Act: -0.0001

Data Index: 850957 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1282684 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1257. Min Act: -0.0001

Data Index: 470337 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1199555 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1141. Min Act: -0.0000

Data Index: 527241 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1136. Min Act: -0.0001

Data Index: 270969 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1112. Min Act: -0.0000

Data Index: 618734 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1104. Min Act: -0.0001

Data Index: 636286 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1107. Min Act: -0.0000

Data Index: 652999 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1086. Min Act: -0.0000

Data Index: 653869 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1037. Min Act: -0.0000

Data Index: 721575 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1027. Min Act: -0.0001

Data Index: 406328 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1009. Min Act: -0.0000

Data Index: 501217 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1067. Min Act: -0.0001

Data Index: 318991 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1072. Min Act: -0.0000

Data Index: 261155 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1308977 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1265012 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0994. Min Act: -0.0000

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1015. Min Act: -0.0000

Data Index: 22377 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1226911 (C4 (Web Text))

Max Activating Token Index: 529