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

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

Neuron 448 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: 3.4086. Min Range: -3.4086

Max Act: 3.3841. Min Act: -0.0000

Data Index: 967966 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.4086. Min Act: -0.0000

Data Index: 274794 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.1753. Min Act: -0.0000

Data Index: 744025 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.2837. Min Act: -0.0000

Data Index: 772630 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.1196. Min Act: -0.0000

Data Index: 597350 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9282. Min Act: -0.0000

Data Index: 246196 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.0534. Min Act: -0.0000

Data Index: 1196930 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9668. Min Act: -0.0000

Data Index: 703608 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9558. Min Act: -0.0000

Data Index: 563976 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9407. Min Act: -0.0000

Data Index: 798425 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.8527. Min Act: -0.0000

Data Index: 813188 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6880. Min Act: -0.0000

Data Index: 524038 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.8370. Min Act: -0.0000

Data Index: 5722 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.7833. Min Act: -0.0000

Data Index: 763870 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9141. Min Act: -0.0000

Data Index: 1243339 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6208. Min Act: -0.0000

Data Index: 899886 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.7311. Min Act: -0.0000

Data Index: 988631 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.0194. Min Act: -0.0000

Data Index: 1172942 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.7512. Min Act: -0.0000

Data Index: 861219 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.7103. Min Act: -0.0000

Data Index: 688355 (C4 (Web Text))

Max Activating Token Index: 25