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

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

Neuron 1307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1051662 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1097852 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1089. Min Act: -0.0002

Data Index: 546970 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1244978 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1081. Min Act: -0.0002

Data Index: 124336 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1096646 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1066. Min Act: -0.0002

Data Index: 819515 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1106. Min Act: -0.0002

Data Index: 341470 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0830. Min Act: -0.0002

Data Index: 665209 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1148487 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0954. Min Act: -0.0002

Data Index: 272526 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0878. Min Act: -0.0002

Data Index: 466915 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1275518 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0838. Min Act: -0.0002

Data Index: 759718 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0801. Min Act: -0.0002

Data Index: 334300 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0897. Min Act: -0.0002

Data Index: 506450 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0929. Min Act: -0.0002

Data Index: 553395 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0929. Min Act: -0.0002

Data Index: 628710 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0912. Min Act: -0.0002

Data Index: 994116 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0909. Min Act: -0.0002

Data Index: 689994 (C4 (Web Text))

Max Activating Token Index: 595