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

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

Neuron 3469 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3289. Min Act: -0.0000

Data Index: 120621 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3188. Min Act: -0.0000

Data Index: 76146 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3190. Min Act: -0.0000

Data Index: 339579 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3257. Min Act: -0.0000

Data Index: 467808 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3110. Min Act: 0.0000

Data Index: 367513 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2898. Min Act: -0.0000

Data Index: 817198 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2950. Min Act: -0.0000

Data Index: 867569 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2831. Min Act: -0.0000

Data Index: 604116 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2930. Min Act: 0.0000

Data Index: 181635 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1223475 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2761. Min Act: -0.0000

Data Index: 579099 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2895. Min Act: -0.0000

Data Index: 932527 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2798. Min Act: -0.0000

Data Index: 499293 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2776. Min Act: -0.0000

Data Index: 830912 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1173630 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2660. Min Act: 0.0000

Data Index: 347535 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2740. Min Act: -0.0000

Data Index: 256962 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2624. Min Act: 0.0000

Data Index: 308813 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2625. Min Act: -0.0000

Data Index: 854853 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2615. Min Act: -0.0000

Data Index: 644091 (C4 (Web Text))

Max Activating Token Index: 908