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

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

Neuron 1899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1143. Min Range: -3.1143

Max Act: 3.1143. Min Act: -0.0001

Data Index: 1387294 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.6700. Min Act: -0.0001

Data Index: 1428225 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.8208. Min Act: -0.0001

Data Index: 1476442 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1496185 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.4184. Min Act: -0.0000

Data Index: 1443822 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1561133 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1651268 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.0378. Min Act: -0.0001

Data Index: 1462545 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1408953 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.2525. Min Act: -0.0001

Data Index: 1495651 (Python Code)

Max Activating Token Index: 923

Text #10

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.1771. Min Act: -0.0000

Data Index: 1559039 (Python Code)

Max Activating Token Index: 855

Text #11

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.1749. Min Act: -0.0000

Data Index: 1613279 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1576189 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.3597. Min Act: -0.0000

Data Index: 1497457 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.1333. Min Act: -0.0001

Data Index: 1531782 (Python Code)

Max Activating Token Index: 923

Text #15

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.3237. Min Act: -0.0000

Data Index: 1424226 (Python Code)

Max Activating Token Index: 990

Text #16

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.2207. Min Act: -0.0000

Data Index: 1563223 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.2024. Min Act: -0.0001

Data Index: 1413923 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.2013. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 3.1143. Min Range: -3.1143

Max Act: 2.0700. Min Act: -0.0001

Data Index: 1480835 (Python Code)

Max Activating Token Index: 43