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

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

Neuron 198 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1387388 (Python Code)

Max Activating Token Index: 1001

Text #1

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1448838 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1516615 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1605782 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1601140 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1514061 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1459404 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1664. Min Act: -0.0000

Data Index: 561037 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1518959 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1553612 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1589. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1541. Min Act: -0.0000

Data Index: 60920 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1533. Min Act: -0.0000

Data Index: 795353 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1587443 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1413942 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1594972 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1586. Min Act: -0.0000

Data Index: 713920 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1505. Min Act: -0.0000

Data Index: 242670 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1449. Min Act: -0.0000

Data Index: 815610 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1500. Min Act: -0.0000

Data Index: 561658 (C4 (Web Text))

Max Activating Token Index: 960