Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2121 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2962. Min Range: -3.2962

Max Act: 3.2962. Min Act: -0.0000

Data Index: 710839 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 3.2962. Min Range: -3.2962

Max Act: 3.1792. Min Act: -0.0000

Data Index: 1181051 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7982. Min Act: -0.0000

Data Index: 768382 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7973. Min Act: -0.0000

Data Index: 758849 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6290. Min Act: -0.0000

Data Index: 1252079 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6133. Min Act: -0.0000

Data Index: 785867 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.3532. Min Act: -0.0000

Data Index: 156108 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5880. Min Act: -0.0000

Data Index: 769906 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5778. Min Act: -0.0000

Data Index: 400439 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5406. Min Act: -0.0000

Data Index: 233042 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6460. Min Act: -0.0000

Data Index: 1165876 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4689. Min Act: -0.0000

Data Index: 702225 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5725. Min Act: -0.0000

Data Index: 180963 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.1874. Min Act: -0.0000

Data Index: 326473 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4526. Min Act: -0.0000

Data Index: 280759 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4356. Min Act: -0.0000

Data Index: 161372 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4424. Min Act: -0.0000

Data Index: 324675 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.2961. Min Act: -0.0000

Data Index: 435226 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.1404. Min Act: -0.0000

Data Index: 776198 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1202910 (C4 (Web Text))

Max Activating Token Index: 434