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

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

Neuron 3816 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2270. Min Range: -1.2270

Max Act: 1.2270. Min Act: -0.0000

Data Index: 347966 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.2270. Min Range: -1.2270

Max Act: 1.1390. Min Act: -0.0000

Data Index: 596579 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1124635 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.8622. Min Act: -0.0000

Data Index: 810069 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.8580. Min Act: -0.0000

Data Index: 721870 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.8000. Min Act: -0.0000

Data Index: 379213 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.8416. Min Act: -0.0000

Data Index: 280890 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.8145. Min Act: -0.0000

Data Index: 75591 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.7236. Min Act: -0.0000

Data Index: 184495 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.7505. Min Act: -0.0000

Data Index: 903810 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.7031. Min Act: -0.0000

Data Index: 818251 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.7051. Min Act: -0.0000

Data Index: 686016 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1284708 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6933. Min Act: -0.0000

Data Index: 619962 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6996. Min Act: -0.0000

Data Index: 669733 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6864. Min Act: -0.0000

Data Index: 203524 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6436. Min Act: -0.0000

Data Index: 6544 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1166138 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.6704. Min Act: -0.0000

Data Index: 884243 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.2270. Min Range: -1.2270

Max Act: 0.7020. Min Act: -0.0000

Data Index: 824732 (C4 (Web Text))

Max Activating Token Index: 946