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

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

Neuron 2195 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: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1050874 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0587. Min Act: -0.0001

Data Index: 996119 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1125786 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1071384 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1244179 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0538. Min Act: -0.0001

Data Index: 809885 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0527. Min Act: -0.0001

Data Index: 80831 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0525. Min Act: -0.0001

Data Index: 890156 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1066097 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0531. Min Act: -0.0001

Data Index: 810385 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0465. Min Act: -0.0001

Data Index: 180378 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0465. Min Act: -0.0001

Data Index: 226359 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1028767 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1104867 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1002923 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0487. Min Act: -0.0001

Data Index: 79105 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0504. Min Act: -0.0001

Data Index: 921264 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0524. Min Act: -0.0001

Data Index: 574035 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0468. Min Act: -0.0001

Data Index: 381347 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0481. Min Act: -0.0001

Data Index: 953427 (C4 (Web Text))

Max Activating Token Index: 686