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

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

Neuron 3961 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: 1.5437. Min Range: -1.5437

Max Act: 1.5437. Min Act: -0.0001

Data Index: 1398637 (Python Code)

Max Activating Token Index: 269

Text #1

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1384202 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.3317. Min Act: -0.0000

Data Index: 553988 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.4646. Min Act: -0.0000

Data Index: 1506360 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1434176 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1554950 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1641404 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.2073. Min Act: -0.0000

Data Index: 883054 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1212158 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1388289 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1905. Min Act: 0.0000

Data Index: 627457 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1498797 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1377258 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 1.5437. Min Range: -1.5437

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1607944 (Python Code)

Max Activating Token Index: 824

Text #14

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1162492 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1599816 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1613803 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 1.5437. Min Range: -1.5437

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1481771 (Python Code)

Max Activating Token Index: 421

Text #18

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1174811 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.5437. Min Range: -1.5437

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1598921 (Python Code)

Max Activating Token Index: 34