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

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

Neuron 960 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: 3.5373. Min Range: -3.5373

Max Act: 3.5373. Min Act: -0.0000

Data Index: 1520738 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 3.5373. Min Range: -3.5373

Max Act: 3.2596. Min Act: -0.0000

Data Index: 1552671 (Python Code)

Max Activating Token Index: 197

Text #2

Max Range: 3.5373. Min Range: -3.5373

Max Act: 3.0689. Min Act: -0.0000

Data Index: 1487406 (Python Code)

Max Activating Token Index: 895

Text #3

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.8803. Min Act: -0.0000

Data Index: 1586159 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1521162 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.8499. Min Act: -0.0000

Data Index: 1512432 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1584026 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.5679. Min Act: -0.0000

Data Index: 1407544 (Python Code)

Max Activating Token Index: 172

Text #8

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.4188. Min Act: -0.0000

Data Index: 1394470 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1415063 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.5206. Min Act: -0.0000

Data Index: 1497768 (Python Code)

Max Activating Token Index: 448

Text #11

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.6413. Min Act: -0.0000

Data Index: 1522542 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1487020 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.7294. Min Act: -0.0000

Data Index: 1485895 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.5696. Min Act: -0.0000

Data Index: 1583442 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.5598. Min Act: -0.0000

Data Index: 1517998 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.8873. Min Act: -0.0000

Data Index: 1554694 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.5330. Min Act: -0.0000

Data Index: 1490336 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.6553. Min Act: -0.0000

Data Index: 1408687 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 3.5373. Min Range: -3.5373

Max Act: 2.4091. Min Act: -0.0000

Data Index: 1506193 (Python Code)

Max Activating Token Index: 661