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

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

Neuron 1673 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: 0.3841. Min Range: -0.3841

Max Act: 0.3841. Min Act: -0.0000

Data Index: 972236 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3758. Min Act: -0.0001

Data Index: 105896 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1081208 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1178164 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3591. Min Act: -0.0000

Data Index: 74273 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1317413 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1281055 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3664. Min Act: -0.0000

Data Index: 168687 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3566. Min Act: -0.0001

Data Index: 56988 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3418. Min Act: -0.0000

Data Index: 822639 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1136392 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3155. Min Act: -0.0000

Data Index: 696181 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3134. Min Act: -0.0000

Data Index: 161014 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3120. Min Act: -0.0000

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3181. Min Act: -0.0001

Data Index: 926196 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3362. Min Act: -0.0001

Data Index: 272043 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3794. Min Act: -0.0000

Data Index: 464650 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3417. Min Act: -0.0000

Data Index: 384898 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2923. Min Act: -0.0000

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 670