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

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

Neuron 3886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8711. Min Act: -0.0001

Data Index: 96648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8588. Min Act: -0.0001

Data Index: 351625 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8330. Min Act: -0.0001

Data Index: 754989 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1337729 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7650. Min Act: -0.0001

Data Index: 736829 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6621. Min Act: -0.0001

Data Index: 169381 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7433. Min Act: -0.0001

Data Index: 222818 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7438. Min Act: -0.0001

Data Index: 762472 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7506. Min Act: -0.0001

Data Index: 756486 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7429. Min Act: -0.0001

Data Index: 1087579 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1187693 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7401. Min Act: -0.0001

Data Index: 451428 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7152. Min Act: -0.0001

Data Index: 681044 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7410. Min Act: -0.0001

Data Index: 90627 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6922. Min Act: -0.0001

Data Index: 12696 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6646. Min Act: -0.0001

Data Index: 86613 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7085. Min Act: -0.0001

Data Index: 344048 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7090. Min Act: -0.0001

Data Index: 703701 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1252625 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7077. Min Act: -0.0001

Data Index: 1104852 (C4 (Web Text))

Max Activating Token Index: 650