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

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

Neuron 2843 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: 5.5678. Min Range: -5.5678

Max Act: 5.2406. Min Act: -0.0000

Data Index: 539894 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.5678. Min Act: -0.0000

Data Index: 899719 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.1968. Min Act: -0.0000

Data Index: 569428 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.3512. Min Act: -0.0000

Data Index: 109623 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.5318. Min Act: -0.0000

Data Index: 1021625 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.2489. Min Act: -0.0001

Data Index: 1048439 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.0228. Min Act: -0.0000

Data Index: 1301225 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.0124. Min Act: -0.0000

Data Index: 103030 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 5.5678. Min Range: -5.5678

Max Act: 5.1418. Min Act: -0.0000

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.4311. Min Act: -0.0000

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.6682. Min Act: -0.0000

Data Index: 388392 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.8233. Min Act: -0.0001

Data Index: 911442 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.7815. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.6958. Min Act: -0.0000

Data Index: 40650 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.6835. Min Act: -0.0000

Data Index: 1297529 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.8700. Min Act: -0.0000

Data Index: 755742 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.4848. Min Act: -0.0001

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.6552. Min Act: -0.0000

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.6690. Min Act: -0.0001

Data Index: 751333 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.4682. Min Act: -0.0001

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 610