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

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

Neuron 1759 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6491. Min Act: -0.0001

Data Index: 336559 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1283749 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6552. Min Act: -0.0001

Data Index: 81373 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6159. Min Act: -0.0001

Data Index: 933511 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6404. Min Act: -0.0001

Data Index: 673145 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5960. Min Act: -0.0001

Data Index: 420501 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6092. Min Act: -0.0001

Data Index: 644543 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6065. Min Act: -0.0001

Data Index: 262065 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1213225 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5969. Min Act: -0.0001

Data Index: 908611 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5709. Min Act: -0.0001

Data Index: 829352 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5926. Min Act: -0.0001

Data Index: 1353293 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5960. Min Act: -0.0001

Data Index: 486426 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5706. Min Act: -0.0001

Data Index: 927468 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5720. Min Act: -0.0001

Data Index: 460975 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5289. Min Act: -0.0001

Data Index: 116549 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6043. Min Act: -0.0001

Data Index: 718147 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5391. Min Act: -0.0001

Data Index: 1159387 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5227. Min Act: -0.0001

Data Index: 526095 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1026287 (C4 (Web Text))

Max Activating Token Index: 476