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

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

Neuron 113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6737. Min Range: -4.6737

Max Act: 4.3348. Min Act: -0.0000

Data Index: 1393538 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 4.6737. Min Range: -4.6737

Max Act: 4.6737. Min Act: -0.0000

Data Index: 1569957 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 4.6737. Min Range: -4.6737

Max Act: 4.1128. Min Act: -0.0000

Data Index: 1482557 (Python Code)

Max Activating Token Index: 423

Text #3

Max Range: 4.6737. Min Range: -4.6737

Max Act: 4.0561. Min Act: -0.0000

Data Index: 1655974 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.7428. Min Act: -0.0000

Data Index: 1372120 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 4.6737. Min Range: -4.6737

Max Act: 4.0607. Min Act: -0.0000

Data Index: 1494162 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.8786. Min Act: -0.0000

Data Index: 1646584 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.8573. Min Act: -0.0000

Data Index: 1479214 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.6758. Min Act: -0.0000

Data Index: 1606845 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.6716. Min Act: -0.0000

Data Index: 1424481 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.9980. Min Act: -0.0000

Data Index: 1410572 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.8173. Min Act: -0.0000

Data Index: 1429094 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.6380. Min Act: -0.0000

Data Index: 1612488 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.9726. Min Act: -0.0000

Data Index: 1465128 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.9771. Min Act: -0.0000

Data Index: 1384584 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.7894. Min Act: -0.0000

Data Index: 1423941 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.6487. Min Act: -0.0000

Data Index: 1579774 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.9437. Min Act: -0.0000

Data Index: 1475325 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.9301. Min Act: -0.0000

Data Index: 1437924 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 4.6737. Min Range: -4.6737

Max Act: 3.7693. Min Act: -0.0000

Data Index: 1361674 (Python Code)

Max Activating Token Index: 596