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

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

Neuron 84 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1078311 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.4687. Min Act: -0.0000

Data Index: 569573 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.4297. Min Act: -0.0000

Data Index: 523434 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1338174 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3573. Min Act: -0.0000

Data Index: 1033715 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1482. Min Act: -0.0000

Data Index: 555772 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0560. Min Act: -0.0000

Data Index: 758727 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1081287 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.4687. Min Range: -1.4687

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1182362 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0881. Min Act: -0.0000

Data Index: 363383 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1057566 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0845. Min Act: -0.0000

Data Index: 384885 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0287. Min Act: -0.0000

Data Index: 865589 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0723. Min Act: -0.0000

Data Index: 682047 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.4687. Min Range: -1.4687

Max Act: 0.9860. Min Act: -0.0000

Data Index: 87010 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.4687. Min Range: -1.4687

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1200918 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0198. Min Act: -0.0000

Data Index: 742388 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.0210. Min Act: -0.0000

Data Index: 949811 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.4687. Min Range: -1.4687

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1001597 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.4687. Min Range: -1.4687

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1294761 (C4 (Web Text))

Max Activating Token Index: 788