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

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

Neuron 1355 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: 5.0554. Min Range: -5.0554

Max Act: 4.8433. Min Act: -0.0000

Data Index: 1429907 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.9677. Min Act: -0.0000

Data Index: 1608444 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6908. Min Act: -0.0000

Data Index: 1564639 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.8460. Min Act: -0.0000

Data Index: 1388210 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 5.0554. Min Range: -5.0554

Max Act: 5.0554. Min Act: -0.0000

Data Index: 1530074 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 5.0554. Min Range: -5.0554

Max Act: 5.0413. Min Act: -0.0000

Data Index: 1474286 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.8580. Min Act: -0.0000

Data Index: 1618546 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6662. Min Act: -0.0000

Data Index: 1453202 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6347. Min Act: -0.0000

Data Index: 1433674 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.7166. Min Act: -0.0000

Data Index: 1585063 (Python Code)

Max Activating Token Index: 701

Text #10

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.7031. Min Act: -0.0000

Data Index: 1644530 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.7442. Min Act: -0.0000

Data Index: 1488673 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6686. Min Act: -0.0000

Data Index: 1361457 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6932. Min Act: -0.0000

Data Index: 1398158 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.6340. Min Act: -0.0000

Data Index: 1589660 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.3747. Min Act: -0.0000

Data Index: 1622711 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.7212. Min Act: -0.0000

Data Index: 1495468 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.5265. Min Act: -0.0000

Data Index: 1564246 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.4950. Min Act: -0.0000

Data Index: 1631864 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 5.0554. Min Range: -5.0554

Max Act: 4.5143. Min Act: -0.0000

Data Index: 1361573 (Python Code)

Max Activating Token Index: 507