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

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

Neuron 2215 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: 1.4955. Min Range: -1.4955

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1335882 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2304. Min Act: -0.0000

Data Index: 343924 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2367. Min Act: -0.0000

Data Index: 978210 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1332630 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.3362. Min Act: -0.0000

Data Index: 380880 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.1841. Min Act: -0.0000

Data Index: 995162 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.1999. Min Act: -0.0000

Data Index: 512615 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1649581 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.0832. Min Act: -0.0000

Data Index: 710806 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1220145 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1452800 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.0254. Min Act: -0.0000

Data Index: 216444 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9445. Min Act: -0.0000

Data Index: 3158 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.0245. Min Act: -0.0000

Data Index: 853401 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9549. Min Act: -0.0000

Data Index: 561060 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9424. Min Act: -0.0000

Data Index: 34990 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1594071 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1189770 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1424216 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 1.4955. Min Range: -1.4955

Max Act: 0.8848. Min Act: -0.0000

Data Index: 465970 (C4 (Web Text))

Max Activating Token Index: 34