Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2865. Min Act: -0.0001

Data Index: 1563871 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1371908 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2489. Min Act: -0.0001

Data Index: 1461746 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2558. Min Act: -0.0001

Data Index: 1492855 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2799. Min Act: -0.0001

Data Index: 1442124 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1492646 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1530. Min Act: -0.0001

Data Index: 1417639 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2168. Min Act: -0.0001

Data Index: 1534965 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.3469. Min Act: -0.0001

Data Index: 1427199 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2757. Min Act: -0.0001

Data Index: 1519686 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2461. Min Act: -0.0001

Data Index: 834295 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1572. Min Act: -0.0001

Data Index: 1567048 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1777. Min Act: -0.0001

Data Index: 1632435 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1703. Min Act: -0.0001

Data Index: 1547332 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1425936 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0704. Min Act: -0.0001

Data Index: 1434380 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1605642 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0700. Min Act: -0.0001

Data Index: 1373953 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0292. Min Act: -0.0001

Data Index: 1496219 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0566. Min Act: -0.0001

Data Index: 1374242 (Python Code)

Max Activating Token Index: 603