Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 641 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3942. Min Range: -2.3942

Max Act: 2.3942. Min Act: -0.0000

Data Index: 1613170 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.7057. Min Act: -0.0000

Data Index: 1475044 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1584903 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1466603 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1613587 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1642164 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1594055 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1552422 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1613968 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1416775 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1417431 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1650289 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1576825 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1387546 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1402892 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1527175 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1485501 (Python Code)

Max Activating Token Index: 867

Text #17

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1439742 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1630724 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 2.3942. Min Range: -2.3942

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1382280 (Python Code)

Max Activating Token Index: 632