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

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

Neuron 5716 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4955. Min Act: -0.0000

Data Index: 974171 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4627. Min Act: -0.0000

Data Index: 602127 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1436359 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4578. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1548395 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3744. Min Act: -0.0000

Data Index: 934753 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1631192 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1520643 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1547031 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1596719 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1454425 (Python Code)

Max Activating Token Index: 522

Text #11

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1654791 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3304. Min Act: -0.0000

Data Index: 618026 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.2882. Min Act: -0.0000

Data Index: 956907 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3387. Min Act: -0.0000

Data Index: 87546 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1576147 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1576776 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1566202 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1588241 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.2595. Min Act: -0.0000

Data Index: 829715 (C4 (Web Text))

Max Activating Token Index: 792