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

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

Neuron 1218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1645704 (Python Code)

Max Activating Token Index: 681

Text #1

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.5384. Min Act: -0.0000

Data Index: 1369581 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1090516 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1436302 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2946. Min Act: -0.0000

Data Index: 370567 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1527753 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1591487 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1254. Min Act: -0.0000

Data Index: 979861 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.2005. Min Act: -0.0000

Data Index: 72474 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1894. Min Act: -0.0000

Data Index: 633484 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1418001 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1522482 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1502449 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0309. Min Act: -0.0000

Data Index: 435405 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1543006 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1573117 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0886. Min Act: -0.0000

Data Index: 558538 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1494181 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1048659 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.6898. Min Range: -1.6898

Max Act: 1.0596. Min Act: -0.0000

Data Index: 358991 (C4 (Web Text))

Max Activating Token Index: 166