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

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

Neuron 3797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7804. Min Range: -4.7804

Max Act: 4.7804. Min Act: -0.0000

Data Index: 583395 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 4.7804. Min Range: -4.7804

Max Act: 3.3819. Min Act: -0.0000

Data Index: 322780 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.7804. Min Range: -4.7804

Max Act: 3.3659. Min Act: -0.0000

Data Index: 192537 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 4.7804. Min Range: -4.7804

Max Act: 3.1523. Min Act: -0.0000

Data Index: 395801 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 4.7804. Min Range: -4.7804

Max Act: 3.3490. Min Act: -0.0000

Data Index: 726778 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.8024. Min Act: -0.0000

Data Index: 859796 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.8025. Min Act: -0.0000

Data Index: 811639 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.7992. Min Act: -0.0000

Data Index: 254926 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.7763. Min Act: -0.0000

Data Index: 97744 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.8719. Min Act: -0.0000

Data Index: 880221 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.7717. Min Act: -0.0000

Data Index: 440901 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.5904. Min Act: -0.0000

Data Index: 118306 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.5460. Min Act: -0.0000

Data Index: 1108498 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1061760 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.3493. Min Act: -0.0000

Data Index: 172611 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.4471. Min Act: -0.0000

Data Index: 917749 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.3071. Min Act: -0.0000

Data Index: 168211 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.2867. Min Act: -0.0000

Data Index: 346630 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.3614. Min Act: -0.0000

Data Index: 864522 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 4.7804. Min Range: -4.7804

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1174693 (C4 (Web Text))

Max Activating Token Index: 79