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

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

Neuron 1626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3722. Min Act: -0.0001

Data Index: 699148 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3379. Min Act: -0.0001

Data Index: 250622 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3052. Min Act: 0.0000

Data Index: 1258645 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1045437 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3240. Min Act: -0.0001

Data Index: 605176 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1205382 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3027. Min Act: -0.0000

Data Index: 921794 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3104. Min Act: -0.0000

Data Index: 767731 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3287. Min Act: -0.0000

Data Index: 961826 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3223. Min Act: 0.0000

Data Index: 1203696 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3211. Min Act: -0.0000

Data Index: 458766 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2966. Min Act: -0.0001

Data Index: 300951 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3125. Min Act: -0.0000

Data Index: 706841 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2882. Min Act: -0.0001

Data Index: 283981 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.3038. Min Act: -0.0001

Data Index: 968479 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2822. Min Act: -0.0000

Data Index: 684772 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2942. Min Act: -0.0001

Data Index: 523587 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2924. Min Act: -0.0000

Data Index: 217302 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2775. Min Act: -0.0001

Data Index: 410980 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.3722. Min Range: -0.3722

Max Act: 0.2871. Min Act: -0.0000

Data Index: 657723 (C4 (Web Text))

Max Activating Token Index: 999