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

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

Neuron 5221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1144503 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2057. Min Act: -0.0001

Data Index: 191661 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2120. Min Act: -0.0001

Data Index: 901966 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1304437 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1988. Min Act: -0.0001

Data Index: 203849 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1518075 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1907. Min Act: -0.0001

Data Index: 394350 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1186915 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1854. Min Act: -0.0001

Data Index: 264800 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1897. Min Act: -0.0001

Data Index: 424469 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1912. Min Act: -0.0001

Data Index: 9594 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1778. Min Act: -0.0001

Data Index: 64368 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1832. Min Act: -0.0001

Data Index: 787118 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1040832 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1935. Min Act: -0.0001

Data Index: 784203 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1008380 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1862. Min Act: -0.0001

Data Index: 246725 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1761. Min Act: -0.0001

Data Index: 178117 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1902. Min Act: -0.0001

Data Index: 270810 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1907. Min Act: -0.0001

Data Index: 280864 (C4 (Web Text))

Max Activating Token Index: 24