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

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

Neuron 2022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1899. Min Act: -0.0000

Data Index: 449236 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0000

Data Index: 217945 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1771. Min Act: -0.0001

Data Index: 280665 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1963. Min Act: -0.0000

Data Index: 238103 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1986. Min Act: -0.0000

Data Index: 329004 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1970. Min Act: -0.0000

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1228369 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1180303 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1047908 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1043944 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1625. Min Act: -0.0000

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1354567 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1581. Min Act: -0.0001

Data Index: 547277 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1418. Min Act: -0.0001

Data Index: 138823 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1218840 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1431. Min Act: -0.0000

Data Index: 816036 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1419. Min Act: -0.0001

Data Index: 830473 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1190212 (C4 (Web Text))

Max Activating Token Index: 280