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

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

Neuron 2157 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: 0.3694. Min Range: -0.3694

Max Act: 0.3694. Min Act: -0.0000

Data Index: 215382 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2858. Min Act: -0.0001

Data Index: 509760 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2740. Min Act: -0.0001

Data Index: 674507 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2845. Min Act: -0.0001

Data Index: 94642 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2908. Min Act: -0.0001

Data Index: 256091 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2610. Min Act: -0.0000

Data Index: 82191 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2698. Min Act: -0.0001

Data Index: 836257 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1184367 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2886. Min Act: -0.0001

Data Index: 204255 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2555. Min Act: -0.0000

Data Index: 659739 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2729. Min Act: -0.0001

Data Index: 646228 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2704. Min Act: -0.0001

Data Index: 877063 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2520. Min Act: -0.0001

Data Index: 771645 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1199738 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2515. Min Act: -0.0001

Data Index: 981452 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2670. Min Act: -0.0001

Data Index: 513858 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1324883 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2661. Min Act: 0.0000

Data Index: 827352 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2715. Min Act: -0.0001

Data Index: 406387 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1126812 (C4 (Web Text))

Max Activating Token Index: 361