Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 597 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.6095. Min Act: -0.0001

Data Index: 774368 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1041606 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5792. Min Act: -0.0001

Data Index: 332429 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5958. Min Act: -0.0001

Data Index: 664764 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5313. Min Act: -0.0001

Data Index: 1120570 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5421. Min Act: -0.0001

Data Index: 987579 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5303. Min Act: -0.0001

Data Index: 1023470 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5634. Min Act: -0.0001

Data Index: 259864 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5433. Min Act: -0.0001

Data Index: 188020 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5541. Min Act: -0.0001

Data Index: 239654 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5084. Min Act: -0.0001

Data Index: 218544 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5238. Min Act: -0.0001

Data Index: 704218 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5033. Min Act: -0.0001

Data Index: 397409 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5123. Min Act: -0.0001

Data Index: 280175 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.5062. Min Act: -0.0001

Data Index: 742988 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4848. Min Act: -0.0001

Data Index: 135296 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4808. Min Act: -0.0001

Data Index: 151172 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1253647 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4596. Min Act: -0.0001

Data Index: 987090 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.6262. Min Range: -0.6262

Max Act: 0.4575. Min Act: -0.0001

Data Index: 150564 (C4 (Web Text))

Max Activating Token Index: 596