Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1415825 (Python Code)

Max Activating Token Index: 902

Text #1

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1444850 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1441267 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1545075 (Python Code)

Max Activating Token Index: 545

Text #4

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1428118 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1532567 (Python Code)

Max Activating Token Index: 435

Text #6

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1637134 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1455180 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1402887 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1453751 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1554053 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1526. Min Act: -0.0001

Data Index: 110856 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1594348 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1477257 (Python Code)

Max Activating Token Index: 510

Text #14

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1442677 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1393125 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1449479 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1627096 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1132390 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1599379 (Python Code)

Max Activating Token Index: 38