Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1386497 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1305. Min Act: -0.0001

Data Index: 289964 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1270. Min Act: -0.0001

Data Index: 629966 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1274. Min Act: -0.0001

Data Index: 217499 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1241. Min Act: -0.0001

Data Index: 856821 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1573075 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1472209 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1144224 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1193. Min Act: -0.0001

Data Index: 644832 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1010. Min Act: -0.0001

Data Index: 919336 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1209642 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1095. Min Act: -0.0001

Data Index: 141183 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1144. Min Act: -0.0001

Data Index: 266529 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1075. Min Act: -0.0001

Data Index: 988419 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1111. Min Act: -0.0001

Data Index: 280516 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1075. Min Act: -0.0001

Data Index: 105025 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1073. Min Act: -0.0001

Data Index: 109505 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1228316 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1210622 (C4 (Web Text))

Max Activating Token Index: 821