Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1178408 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4945. Min Act: -0.0001

Data Index: 507759 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4623. Min Act: -0.0001

Data Index: 335714 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4710. Min Act: -0.0001

Data Index: 455874 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4629. Min Act: -0.0001

Data Index: 519625 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1156415 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4434. Min Act: -0.0001

Data Index: 824251 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1283206 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4767. Min Act: -0.0001

Data Index: 792548 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4432. Min Act: -0.0001

Data Index: 175488 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1121681 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4223. Min Act: -0.0001

Data Index: 544714 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3932. Min Act: -0.0001

Data Index: 566877 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4200. Min Act: -0.0001

Data Index: 556642 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4196. Min Act: -0.0001

Data Index: 269281 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1355441 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4391. Min Act: -0.0001

Data Index: 885615 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1251789 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4216. Min Act: -0.0001

Data Index: 184289 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4220. Min Act: -0.0001

Data Index: 892590 (C4 (Web Text))

Max Activating Token Index: 609