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

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

Neuron 2207 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: 0.8745. Min Range: -0.8745

Max Act: 0.8745. Min Act: -0.0001

Data Index: 570777 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8387. Min Act: -0.0001

Data Index: 399275 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8692. Min Act: -0.0001

Data Index: 540377 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8307. Min Act: -0.0001

Data Index: 1115256 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1260149 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8010. Min Act: -0.0001

Data Index: 578131 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7725. Min Act: -0.0001

Data Index: 539448 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8004. Min Act: -0.0001

Data Index: 154093 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8049. Min Act: -0.0001

Data Index: 879082 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7715. Min Act: -0.0000

Data Index: 924863 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7424. Min Act: -0.0001

Data Index: 751321 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7616. Min Act: -0.0001

Data Index: 942063 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1126034 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7585. Min Act: -0.0001

Data Index: 739735 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7520. Min Act: -0.0001

Data Index: 698583 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7483. Min Act: -0.0001

Data Index: 314356 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7261. Min Act: -0.0001

Data Index: 686379 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7223. Min Act: -0.0001

Data Index: 289190 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1105088 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7112. Min Act: -0.0001

Data Index: 966393 (C4 (Web Text))

Max Activating Token Index: 874