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

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

Neuron 96 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.4851. Min Act: -0.0000

Data Index: 345427 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2772. Min Act: -0.0000

Data Index: 576818 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1286420 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2995. Min Act: -0.0000

Data Index: 625376 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1344418 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1129021 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2695. Min Act: -0.0000

Data Index: 290888 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1256449 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1232737 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.3289. Min Act: -0.0000

Data Index: 417923 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.2421. Min Act: -0.0000

Data Index: 909849 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1216956 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1212. Min Act: -0.0000

Data Index: 424809 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1322036 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1688. Min Act: -0.0000

Data Index: 283909 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1298. Min Act: -0.0000

Data Index: 239766 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.0816. Min Act: -0.0000

Data Index: 462332 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1250. Min Act: -0.0000

Data Index: 527 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1323. Min Act: -0.0000

Data Index: 931927 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.4851. Min Range: -1.4851

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1129483 (C4 (Web Text))

Max Activating Token Index: 646