Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5332 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1294. Min Act: -0.0001

Data Index: 577760 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1002560 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1326. Min Act: -0.0001

Data Index: 366059 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1220. Min Act: -0.0001

Data Index: 972362 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1242. Min Act: -0.0001

Data Index: 585609 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1185. Min Act: -0.0001

Data Index: 382081 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1039. Min Act: -0.0001

Data Index: 417633 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1136. Min Act: -0.0001

Data Index: 922165 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1166. Min Act: -0.0001

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1112802 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1051. Min Act: -0.0001

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1076. Min Act: -0.0001

Data Index: 596585 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1070. Min Act: -0.0001

Data Index: 31098 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1044644 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1100. Min Act: -0.0001

Data Index: 300905 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1023980 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1019. Min Act: -0.0001

Data Index: 947114 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1183436 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1060. Min Act: -0.0001

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1070. Min Act: -0.0001

Data Index: 651952 (C4 (Web Text))

Max Activating Token Index: 139