Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0001

Data Index: 555850 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1187. Min Act: -0.0001

Data Index: 267296 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1229. Min Act: -0.0001

Data Index: 642010 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1165. Min Act: -0.0001

Data Index: 961726 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1144. Min Act: -0.0001

Data Index: 411416 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1041102 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1131. Min Act: -0.0001

Data Index: 226596 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1040486 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1323902 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1178602 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1014. Min Act: -0.0001

Data Index: 525354 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1077. Min Act: -0.0001

Data Index: 335434 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1188. Min Act: -0.0001

Data Index: 695804 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1098. Min Act: -0.0001

Data Index: 807562 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1048. Min Act: -0.0001

Data Index: 970674 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0969. Min Act: -0.0001

Data Index: 875674 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1041. Min Act: -0.0001

Data Index: 243437 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1072329 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1064. Min Act: -0.0001

Data Index: 162581 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0988. Min Act: -0.0001

Data Index: 257401 (C4 (Web Text))

Max Activating Token Index: 855