Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1748 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1327. Min Act: -0.0006

Data Index: 655065 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1329. Min Act: -0.0006

Data Index: 990866 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1305. Min Act: -0.0006

Data Index: 1230633 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1222. Min Act: -0.0006

Data Index: 344997 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1216. Min Act: -0.0006

Data Index: 1072636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1254. Min Act: -0.0006

Data Index: 922043 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1242. Min Act: -0.0006

Data Index: 1124351 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1199. Min Act: -0.0006

Data Index: 471747 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1261. Min Act: -0.0006

Data Index: 766436 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1166. Min Act: -0.0006

Data Index: 225500 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1165. Min Act: -0.0006

Data Index: 421784 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1122. Min Act: -0.0006

Data Index: 680481 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1104. Min Act: -0.0006

Data Index: 1254128 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1102. Min Act: -0.0006

Data Index: 753791 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1060. Min Act: -0.0006

Data Index: 255208 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1100. Min Act: -0.0006

Data Index: 300873 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1059. Min Act: -0.0006

Data Index: 1101278 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1083. Min Act: -0.0006

Data Index: 261958 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1064. Min Act: -0.0006

Data Index: 1173897 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1066. Min Act: -0.0006

Data Index: 169282 (C4 (Web Text))

Max Activating Token Index: 360