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

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

Neuron 1986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2658. Min Range: -2.2658

Max Act: 2.1929. Min Act: -0.0000

Data Index: 913805 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9367. Min Act: -0.0001

Data Index: 551530 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 2.2658. Min Range: -2.2658

Max Act: 2.2583. Min Act: -0.0000

Data Index: 316507 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 2.2658. Min Range: -2.2658

Max Act: 2.2658. Min Act: -0.0000

Data Index: 948799 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.2658. Min Range: -2.2658

Max Act: 2.1183. Min Act: -0.0001

Data Index: 938294 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1066703 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9590. Min Act: -0.0001

Data Index: 51200 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 2.2658. Min Range: -2.2658

Max Act: 2.0025. Min Act: -0.0001

Data Index: 643867 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9978. Min Act: -0.0000

Data Index: 427414 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9993. Min Act: -0.0000

Data Index: 680951 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9731. Min Act: -0.0001

Data Index: 313356 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9669. Min Act: -0.0000

Data Index: 251822 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.9100. Min Act: -0.0000

Data Index: 409776 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.7955. Min Act: -0.0001

Data Index: 826524 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.8897. Min Act: -0.0001

Data Index: 754586 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.7109. Min Act: -0.0000

Data Index: 144104 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1054754 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.8544. Min Act: -0.0001

Data Index: 1055353 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.7523. Min Act: -0.0000

Data Index: 789701 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 2.2658. Min Range: -2.2658

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1223104 (C4 (Web Text))

Max Activating Token Index: 230