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

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

Neuron 2667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2883. Min Act: -0.0001

Data Index: 427178 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2762. Min Act: -0.0001

Data Index: 700944 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1098531 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1253072 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2631. Min Act: -0.0001

Data Index: 683633 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2761. Min Act: -0.0001

Data Index: 762413 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2800. Min Act: -0.0001

Data Index: 10333 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2672. Min Act: -0.0001

Data Index: 593700 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2593. Min Act: -0.0001

Data Index: 1088675 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2623. Min Act: -0.0001

Data Index: 875639 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2539. Min Act: -0.0001

Data Index: 562616 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2622. Min Act: -0.0001

Data Index: 939546 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1240679 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1039582 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2425. Min Act: -0.0001

Data Index: 611814 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1164887 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2339. Min Act: -0.0001

Data Index: 895631 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2348. Min Act: -0.0001

Data Index: 485148 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1221676 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1023193 (C4 (Web Text))

Max Activating Token Index: 708