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

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

Neuron 678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1347620 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.5270. Min Act: -0.0000

Data Index: 553678 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.3002. Min Act: -0.0000

Data Index: 167158 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.2478. Min Act: -0.0000

Data Index: 25530 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8544. Min Act: -0.0000

Data Index: 254356 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8189. Min Act: -0.0000

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8485. Min Act: -0.0000

Data Index: 970475 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.7113. Min Act: -0.0000

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.6051. Min Act: -0.0000

Data Index: 400738 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.6004. Min Act: -0.0000

Data Index: 452164 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5871. Min Act: -0.0000

Data Index: 321289 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.6143. Min Act: -0.0000

Data Index: 179417 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5837. Min Act: -0.0000

Data Index: 607081 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5580. Min Act: -0.0000

Data Index: 866794 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5487. Min Act: -0.0000

Data Index: 974454 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5700. Min Act: -0.0000

Data Index: 737119 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5548. Min Act: -0.0000

Data Index: 311803 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5450. Min Act: -0.0000

Data Index: 552448 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.4969. Min Act: -0.0000

Data Index: 491510 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.5086. Min Act: -0.0000

Data Index: 384430 (C4 (Web Text))

Max Activating Token Index: 428