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

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

Neuron 4734 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: 1.4079. Min Range: -1.4079

Max Act: 1.4079. Min Act: -0.0001

Data Index: 1200470 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.3085. Min Act: -0.0001

Data Index: 1045793 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.3096. Min Act: -0.0001

Data Index: 1171012 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2701. Min Act: -0.0001

Data Index: 757163 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2711. Min Act: -0.0001

Data Index: 891428 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.2162. Min Act: -0.0001

Data Index: 1502605 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1590. Min Act: -0.0001

Data Index: 1144484 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1366. Min Act: -0.0001

Data Index: 27181 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0780. Min Act: -0.0001

Data Index: 265298 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1333. Min Act: -0.0001

Data Index: 362729 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0339. Min Act: -0.0001

Data Index: 538370 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0904. Min Act: -0.0001

Data Index: 738316 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.1114. Min Act: -0.0001

Data Index: 903488 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0944. Min Act: -0.0001

Data Index: 887031 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0649. Min Act: -0.0001

Data Index: 792667 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0383. Min Act: -0.0001

Data Index: 370785 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.4079. Min Range: -1.4079

Max Act: 1.0745. Min Act: -0.0001

Data Index: 220083 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.4079. Min Range: -1.4079

Max Act: 0.9822. Min Act: -0.0001

Data Index: 826014 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.4079. Min Range: -1.4079

Max Act: 0.9995. Min Act: -0.0001

Data Index: 81637 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.4079. Min Range: -1.4079

Max Act: 0.9956. Min Act: -0.0001

Data Index: 837187 (C4 (Web Text))

Max Activating Token Index: 31