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

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

Neuron 2722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2846. Min Act: -0.0001

Data Index: 957215 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1059667 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1696. Min Act: -0.0001

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1710. Min Act: -0.0001

Data Index: 89009 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1436. Min Act: -0.0001

Data Index: 821838 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1009730 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1384846 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1530. Min Act: -0.0001

Data Index: 969371 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1410. Min Act: -0.0001

Data Index: 650048 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1057117 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1427. Min Act: -0.0001

Data Index: 638536 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1330793 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1309. Min Act: -0.0001

Data Index: 107705 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1470855 (Python Code)

Max Activating Token Index: 92

Text #15

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1380089 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1338964 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1324. Min Act: -0.0001

Data Index: 356530 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1365. Min Act: -0.0001

Data Index: 352811 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1345432 (C4 (Web Text))

Max Activating Token Index: 14