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

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

Neuron 1774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2350. Min Act: -0.0000

Data Index: 529685 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2244. Min Act: -0.0000

Data Index: 181470 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1085872 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1069477 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1890. Min Act: -0.0000

Data Index: 246183 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1886. Min Act: -0.0000

Data Index: 947078 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1768. Min Act: -0.0000

Data Index: 59521 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1883. Min Act: -0.0000

Data Index: 513261 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1220456 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1626. Min Act: -0.0000

Data Index: 937341 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1542. Min Act: -0.0000

Data Index: 297301 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1653. Min Act: -0.0000

Data Index: 709566 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1029643 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1072528 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1253659 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1495. Min Act: -0.0000

Data Index: 407375 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1519. Min Act: -0.0000

Data Index: 279128 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1505. Min Act: -0.0000

Data Index: 229923 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1492. Min Act: -0.0000

Data Index: 183223 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1480. Min Act: -0.0000

Data Index: 256224 (C4 (Web Text))

Max Activating Token Index: 1002