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

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

Neuron 2872 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: 0.6516. Min Range: -0.6516

Max Act: 0.6516. Min Act: -0.0001

Data Index: 753832 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.6296. Min Act: -0.0001

Data Index: 658836 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5888. Min Act: -0.0001

Data Index: 1259694 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.6118. Min Act: -0.0001

Data Index: 869038 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5795. Min Act: -0.0001

Data Index: 119044 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5493. Min Act: -0.0001

Data Index: 100499 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5711. Min Act: -0.0001

Data Index: 1077138 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5811. Min Act: -0.0001

Data Index: 905097 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5377. Min Act: -0.0001

Data Index: 550122 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5402. Min Act: -0.0001

Data Index: 751423 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5036. Min Act: -0.0001

Data Index: 1145956 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5042. Min Act: -0.0001

Data Index: 857147 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1343140 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5025. Min Act: -0.0001

Data Index: 1084278 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1274842 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5322. Min Act: -0.0001

Data Index: 285529 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5253. Min Act: -0.0001

Data Index: 426501 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1158853 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.6516. Min Range: -0.6516

Max Act: 0.5056. Min Act: -0.0001

Data Index: 765765 (C4 (Web Text))

Max Activating Token Index: 529