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

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

Neuron 290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.7501. Min Act: -0.0001

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.4705. Min Act: -0.0001

Data Index: 77818 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.4706. Min Act: -0.0001

Data Index: 53598 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.4730. Min Act: -0.0001

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.4688. Min Act: -0.0001

Data Index: 521666 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.4022. Min Act: -0.0001

Data Index: 483461 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.3697. Min Act: -0.0001

Data Index: 788174 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.3466. Min Act: -0.0001

Data Index: 291087 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.3060. Min Act: -0.0001

Data Index: 1095296 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.2542. Min Act: -0.0001

Data Index: 872265 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.2435. Min Act: -0.0001

Data Index: 220196 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1046755 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.1940. Min Act: -0.0001

Data Index: 621330 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.2282. Min Act: -0.0001

Data Index: 1149459 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.2160. Min Act: -0.0001

Data Index: 147790 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.1915. Min Act: -0.0001

Data Index: 234908 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.0920. Min Act: -0.0001

Data Index: 7591 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.1441. Min Act: -0.0001

Data Index: 144246 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.1796. Min Act: -0.0001

Data Index: 382064 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.7501. Min Range: -1.7501

Max Act: 1.1629. Min Act: -0.0001

Data Index: 955828 (C4 (Web Text))

Max Activating Token Index: 183