Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3787 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3154. Min Range: -3.3154

Max Act: 3.3154. Min Act: -0.0001

Data Index: 418008 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 3.3154. Min Range: -3.3154

Max Act: 3.1714. Min Act: -0.0001

Data Index: 588878 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 3.3154. Min Range: -3.3154

Max Act: 3.2414. Min Act: -0.0001

Data Index: 315524 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.3154. Min Range: -3.3154

Max Act: 3.0582. Min Act: -0.0000

Data Index: 1147308 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.3154. Min Range: -3.3154

Max Act: 3.1229. Min Act: -0.0001

Data Index: 347282 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.8963. Min Act: -0.0001

Data Index: 1149973 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.9301. Min Act: -0.0001

Data Index: 509048 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.8679. Min Act: -0.0001

Data Index: 1105299 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6646. Min Act: -0.0000

Data Index: 440736 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.9425. Min Act: -0.0001

Data Index: 620961 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6309. Min Act: -0.0001

Data Index: 784849 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.7108. Min Act: -0.0001

Data Index: 1050880 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.7505. Min Act: -0.0001

Data Index: 587522 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6675. Min Act: -0.0000

Data Index: 18873 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.9531. Min Act: -0.0001

Data Index: 830937 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6494. Min Act: -0.0001

Data Index: 829277 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6820. Min Act: -0.0000

Data Index: 728125 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.7968. Min Act: -0.0001

Data Index: 233834 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.8396. Min Act: -0.0000

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 3.3154. Min Range: -3.3154

Max Act: 2.6449. Min Act: -0.0001

Data Index: 68799 (C4 (Web Text))

Max Activating Token Index: 910