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

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

Neuron 4135 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0592. Min Range: -4.0592

Max Act: 4.0592. Min Act: -0.0000

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.7473. Min Act: -0.0000

Data Index: 713690 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.6103. Min Act: -0.0000

Data Index: 967922 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 4.0592. Min Range: -4.0592

Max Act: 4.0036. Min Act: -0.0000

Data Index: 1222978 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.4133. Min Act: -0.0000

Data Index: 266729 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.6590. Min Act: -0.0000

Data Index: 80646 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1225. Min Act: -0.0000

Data Index: 872012 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.4998. Min Act: -0.0000

Data Index: 397824 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.4976. Min Act: -0.0000

Data Index: 803758 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.4815. Min Act: -0.0000

Data Index: 805558 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1597. Min Act: -0.0000

Data Index: 717298 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1274. Min Act: -0.0000

Data Index: 913552 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.2385. Min Act: -0.0000

Data Index: 430340 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.2027. Min Act: -0.0000

Data Index: 567781 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.3188. Min Act: -0.0000

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1644. Min Act: -0.0000

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1405. Min Act: -0.0000

Data Index: 725968 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 4.0592. Min Range: -4.0592

Max Act: 2.9586. Min Act: -0.0000

Data Index: 134225 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1377. Min Act: -0.0000

Data Index: 581159 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 4.0592. Min Range: -4.0592

Max Act: 3.1100. Min Act: -0.0000

Data Index: 1049725 (C4 (Web Text))

Max Activating Token Index: 625