Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3843 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0629. Min Act: -0.0001

Data Index: 666837 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1300741 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0625. Min Act: -0.0001

Data Index: 981413 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0623. Min Act: -0.0001

Data Index: 860988 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0596. Min Act: -0.0001

Data Index: 972648 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0634. Min Act: -0.0001

Data Index: 233560 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0577. Min Act: -0.0001

Data Index: 541007 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0499. Min Act: -0.0001

Data Index: 997123 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0561. Min Act: -0.0001

Data Index: 760551 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0515. Min Act: -0.0001

Data Index: 714121 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0505. Min Act: -0.0001

Data Index: 830883 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1346264 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0538. Min Act: -0.0001

Data Index: 290052 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0524. Min Act: -0.0001

Data Index: 565959 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1215006 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0507. Min Act: -0.0001

Data Index: 928406 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1256765 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1143062 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0455. Min Act: -0.0002

Data Index: 218152 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1095359 (C4 (Web Text))

Max Activating Token Index: 135