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

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

Neuron 756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3356. Min Act: -0.0001

Data Index: 503679 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3217. Min Act: -0.0001

Data Index: 761151 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3300. Min Act: -0.0001

Data Index: 563650 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3252. Min Act: -0.0001

Data Index: 320618 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3102. Min Act: -0.0001

Data Index: 835706 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3018. Min Act: -0.0001

Data Index: 416234 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2985. Min Act: -0.0001

Data Index: 782654 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3049. Min Act: -0.0001

Data Index: 358208 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1143423 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2572. Min Act: -0.0001

Data Index: 968812 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2656. Min Act: -0.0001

Data Index: 246357 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2504. Min Act: -0.0000

Data Index: 718591 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2354. Min Act: -0.0001

Data Index: 801543 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2632. Min Act: -0.0001

Data Index: 60173 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2690. Min Act: -0.0001

Data Index: 13053 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2587. Min Act: -0.0001

Data Index: 374666 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2331. Min Act: -0.0001

Data Index: 319928 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2325. Min Act: -0.0001

Data Index: 1231327 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2555. Min Act: -0.0001

Data Index: 206037 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2530. Min Act: -0.0001

Data Index: 385286 (C4 (Web Text))

Max Activating Token Index: 696