Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2673 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3749. Min Act: -0.0001

Data Index: 1329039 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3373. Min Act: -0.0001

Data Index: 943909 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3486. Min Act: -0.0001

Data Index: 875938 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3382. Min Act: -0.0001

Data Index: 671535 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3499. Min Act: -0.0001

Data Index: 594136 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3454. Min Act: -0.0001

Data Index: 757952 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3207. Min Act: -0.0001

Data Index: 211976 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3109. Min Act: -0.0001

Data Index: 533577 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1318480 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2961. Min Act: -0.0001

Data Index: 1260777 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1078547 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2646. Min Act: -0.0001

Data Index: 298298 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2772. Min Act: -0.0001

Data Index: 429287 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1178440 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2694. Min Act: -0.0001

Data Index: 217619 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2720. Min Act: -0.0001

Data Index: 381283 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2710. Min Act: -0.0001

Data Index: 243080 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2852. Min Act: -0.0001

Data Index: 440894 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2589. Min Act: -0.0001

Data Index: 2773 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2661. Min Act: -0.0001

Data Index: 646357 (C4 (Web Text))

Max Activating Token Index: 337