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

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

Neuron 4377 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: 4.0857. Min Range: -4.0857

Max Act: 4.0857. Min Act: -0.0000

Data Index: 617463 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.6177. Min Act: -0.0000

Data Index: 1043210 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.4296. Min Act: -0.0000

Data Index: 976220 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.3108. Min Act: -0.0000

Data Index: 783177 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.9305. Min Act: -0.0000

Data Index: 525246 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.3593. Min Act: -0.0000

Data Index: 1174747 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.0113. Min Act: -0.0000

Data Index: 1317045 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.0604. Min Act: -0.0000

Data Index: 669486 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.8908. Min Act: -0.0000

Data Index: 776153 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.9633. Min Act: -0.0000

Data Index: 1024384 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.0123. Min Act: -0.0000

Data Index: 458765 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.0122. Min Act: -0.0000

Data Index: 419579 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.8645. Min Act: -0.0000

Data Index: 805350 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.7190. Min Act: -0.0000

Data Index: 524448 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.8458. Min Act: -0.0000

Data Index: 1084927 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.9525. Min Act: -0.0000

Data Index: 1314160 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.7995. Min Act: -0.0000

Data Index: 343393 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.7879. Min Act: -0.0000

Data Index: 795746 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.6405. Min Act: -0.0000

Data Index: 1257945 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 4.0857. Min Range: -4.0857

Max Act: 2.7736. Min Act: -0.0000

Data Index: 328773 (C4 (Web Text))

Max Activating Token Index: 901