Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 584 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8984. Min Act: -0.0000

Data Index: 575535 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7787. Min Act: -0.0000

Data Index: 511375 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7753. Min Act: -0.0000

Data Index: 2321 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1082988 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1122468 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7392. Min Act: -0.0000

Data Index: 543837 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6203. Min Act: -0.0000

Data Index: 259843 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5922. Min Act: -0.0000

Data Index: 759782 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6586. Min Act: -0.0000

Data Index: 646283 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5749. Min Act: -0.0000

Data Index: 224389 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6275. Min Act: -0.0000

Data Index: 829419 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1374437 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6155. Min Act: -0.0000

Data Index: 209237 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1531293 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5894. Min Act: -0.0000

Data Index: 162859 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6050. Min Act: -0.0000

Data Index: 527732 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1204832 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5821. Min Act: -0.0000

Data Index: 455630 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5845. Min Act: -0.0000

Data Index: 451454 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5482. Min Act: -0.0000

Data Index: 335668 (C4 (Web Text))

Max Activating Token Index: 168