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

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

Neuron 1187 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1242. Min Range: -1.1242

Max Act: 1.1242. Min Act: -0.0000

Data Index: 130007 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1007785 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.9370. Min Act: -0.0000

Data Index: 757697 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.8410. Min Act: -0.0000

Data Index: 423 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.8628. Min Act: -0.0000

Data Index: 963079 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.8027. Min Act: -0.0000

Data Index: 634181 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7626. Min Act: -0.0000

Data Index: 352653 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6443. Min Act: -0.0000

Data Index: 359648 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7203. Min Act: -0.0000

Data Index: 915351 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7357. Min Act: -0.0000

Data Index: 641059 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7126. Min Act: -0.0000

Data Index: 446072 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7171. Min Act: 0.0000

Data Index: 969519 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6599. Min Act: -0.0000

Data Index: 147186 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6839. Min Act: -0.0000

Data Index: 47416 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1084863 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6588. Min Act: -0.0000

Data Index: 712005 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6953. Min Act: -0.0000

Data Index: 226406 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1103897 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1205968 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 1.1242. Min Range: -1.1242

Max Act: 0.6663. Min Act: -0.0000

Data Index: 792035 (C4 (Web Text))

Max Activating Token Index: 671