Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4458. Min Act: -0.0001

Data Index: 1146029 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4545. Min Act: -0.0001

Data Index: 467503 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4481. Min Act: -0.0001

Data Index: 870920 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4288. Min Act: -0.0001

Data Index: 776188 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4017. Min Act: -0.0001

Data Index: 395481 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4403. Min Act: -0.0001

Data Index: 266902 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4013. Min Act: -0.0001

Data Index: 582998 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3906. Min Act: -0.0001

Data Index: 971088 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3925. Min Act: -0.0000

Data Index: 129244 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3719. Min Act: -0.0001

Data Index: 1279258 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3756. Min Act: -0.0001

Data Index: 717 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3759. Min Act: -0.0001

Data Index: 652443 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3806. Min Act: -0.0001

Data Index: 989334 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1206914 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3687. Min Act: -0.0001

Data Index: 784119 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3870. Min Act: -0.0001

Data Index: 253790 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3634. Min Act: -0.0001

Data Index: 539869 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1282989 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3650. Min Act: -0.0001

Data Index: 763990 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3639. Min Act: -0.0001

Data Index: 188962 (C4 (Web Text))

Max Activating Token Index: 137