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

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

Neuron 1212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7788. Min Act: -0.0001

Data Index: 300217 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7487. Min Act: -0.0001

Data Index: 181416 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7653. Min Act: -0.0001

Data Index: 229933 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7229. Min Act: -0.0001

Data Index: 835286 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7681. Min Act: -0.0001

Data Index: 1056575 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.8231. Min Act: -0.0001

Data Index: 752422 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7886. Min Act: -0.0001

Data Index: 625969 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7376. Min Act: -0.0001

Data Index: 392476 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7833. Min Act: -0.0001

Data Index: 577547 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7123. Min Act: -0.0001

Data Index: 202375 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7828. Min Act: -0.0001

Data Index: 281004 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6907. Min Act: -0.0001

Data Index: 762439 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1288695 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7463. Min Act: -0.0001

Data Index: 877028 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7315. Min Act: -0.0001

Data Index: 1129941 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7896. Min Act: -0.0001

Data Index: 172975 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7606. Min Act: -0.0001

Data Index: 1126220 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7287. Min Act: -0.0001

Data Index: 678897 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7403. Min Act: -0.0001

Data Index: 481854 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7357. Min Act: -0.0001

Data Index: 1158117 (C4 (Web Text))

Max Activating Token Index: 385