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

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

Neuron 2740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: -0.0001

Data Index: 697804 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1012909 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1093. Min Act: -0.0001

Data Index: 432347 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1204. Min Act: -0.0001

Data Index: 831063 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1098. Min Act: -0.0001

Data Index: 71816 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1136107 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1060207 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1181. Min Act: -0.0001

Data Index: 257165 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1128. Min Act: -0.0001

Data Index: 392531 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1207652 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1003871 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1044. Min Act: -0.0001

Data Index: 620578 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1074. Min Act: -0.0001

Data Index: 15692 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1096. Min Act: -0.0001

Data Index: 522503 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1186639 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1025. Min Act: -0.0001

Data Index: 962967 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0988. Min Act: -0.0001

Data Index: 341038 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1017. Min Act: -0.0001

Data Index: 80811 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0982. Min Act: -0.0001

Data Index: 332617 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1041. Min Act: -0.0001

Data Index: 523098 (C4 (Web Text))

Max Activating Token Index: 9