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

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

Neuron 2176 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: 0.1204. Min Range: -0.1204

Max Act: 0.1204. Min Act: -0.0001

Data Index: 390958 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1219986 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1163568 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1235738 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1099. Min Act: -0.0001

Data Index: 255280 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1094. Min Act: -0.0001

Data Index: 425620 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1110. Min Act: -0.0001

Data Index: 147084 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1623412 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1050606 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1074126 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1060. Min Act: -0.0001

Data Index: 401198 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1058. Min Act: -0.0001

Data Index: 387990 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1247633 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1017. Min Act: -0.0001

Data Index: 734245 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1048. Min Act: -0.0001

Data Index: 793188 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1048. Min Act: -0.0001

Data Index: 508877 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1039. Min Act: -0.0001

Data Index: 565106 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1033. Min Act: -0.0001

Data Index: 853035 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1259718 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1104028 (C4 (Web Text))

Max Activating Token Index: 590