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

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

Neuron 5130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.4066. Min Act: -0.0000

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.3447. Min Act: -0.0000

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.3378. Min Act: -0.0000

Data Index: 813739 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.3900. Min Act: -0.0000

Data Index: 554901 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2092. Min Act: -0.0000

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2968. Min Act: -0.0000

Data Index: 107255 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2138. Min Act: -0.0000

Data Index: 890393 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1612439 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1125728 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2318. Min Act: -0.0000

Data Index: 485542 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2240. Min Act: -0.0000

Data Index: 924331 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2734. Min Act: -0.0000

Data Index: 173756 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1631288 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2294. Min Act: -0.0000

Data Index: 950415 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2760. Min Act: -0.0000

Data Index: 543112 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1266603 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1935. Min Act: -0.0000

Data Index: 414721 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.1969. Min Act: -0.0000

Data Index: 641246 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2266. Min Act: -0.0000

Data Index: 544674 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.4066. Min Range: -1.4066

Max Act: 1.2272. Min Act: -0.0000

Data Index: 260304 (C4 (Web Text))

Max Activating Token Index: 410