Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0003

Data Index: 1078700 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1213. Min Act: -0.0003

Data Index: 1211743 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1133. Min Act: -0.0003

Data Index: 992557 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1181. Min Act: -0.0003

Data Index: 308596 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1159182 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1032. Min Act: -0.0003

Data Index: 584608 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1184. Min Act: -0.0003

Data Index: 841049 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1020. Min Act: -0.0003

Data Index: 754757 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0953. Min Act: -0.0003

Data Index: 1121880 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1094. Min Act: -0.0003

Data Index: 529404 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1329930 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1049. Min Act: -0.0003

Data Index: 159064 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0966. Min Act: -0.0003

Data Index: 171675 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0997. Min Act: -0.0003

Data Index: 1444236 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0990. Min Act: -0.0003

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0999. Min Act: -0.0003

Data Index: 365857 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1033. Min Act: -0.0003

Data Index: 41259 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1057. Min Act: -0.0003

Data Index: 329193 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0975. Min Act: -0.0003

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 620