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

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

Neuron 475 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: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0001

Data Index: 116198 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1342. Min Act: -0.0001

Data Index: 283519 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1241. Min Act: -0.0001

Data Index: 287014 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0974. Min Act: -0.0001

Data Index: 530401 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1345262 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1059. Min Act: -0.0001

Data Index: 317354 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1100162 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1119. Min Act: -0.0001

Data Index: 736160 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0988. Min Act: -0.0001

Data Index: 948577 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1143. Min Act: -0.0001

Data Index: 994517 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0972. Min Act: -0.0001

Data Index: 145689 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1030482 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1079. Min Act: -0.0001

Data Index: 496357 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0968. Min Act: -0.0001

Data Index: 66376 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1039241 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1233482 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1002. Min Act: -0.0001

Data Index: 171241 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1190628 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0964. Min Act: -0.0001

Data Index: 474060 (C4 (Web Text))

Max Activating Token Index: 165