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

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

Neuron 3457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4980. Min Range: -2.4980

Max Act: 2.4980. Min Act: -0.0000

Data Index: 54487 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 2.4980. Min Range: -2.4980

Max Act: 2.2469. Min Act: -0.0000

Data Index: 119666 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 2.4980. Min Range: -2.4980

Max Act: 2.2601. Min Act: -0.0000

Data Index: 846542 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.8728. Min Act: -0.0001

Data Index: 187845 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.7106. Min Act: -0.0000

Data Index: 283625 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.7224. Min Act: -0.0001

Data Index: 265065 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.5745. Min Act: -0.0000

Data Index: 207483 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1128156 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.5805. Min Act: -0.0000

Data Index: 1007564 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.5872. Min Act: -0.0000

Data Index: 678844 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4420. Min Act: -0.0000

Data Index: 1314240 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4785. Min Act: -0.0000

Data Index: 66132 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4926. Min Act: -0.0001

Data Index: 1159504 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4978. Min Act: -0.0000

Data Index: 365829 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1281579 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4142. Min Act: -0.0000

Data Index: 594004 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4984. Min Act: -0.0000

Data Index: 672509 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4148. Min Act: -0.0001

Data Index: 1307096 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.3743. Min Act: -0.0000

Data Index: 34186 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.4980. Min Range: -2.4980

Max Act: 1.4089. Min Act: -0.0000

Data Index: 385896 (C4 (Web Text))

Max Activating Token Index: 1011