Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5643 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7180. Min Range: -2.7180

Max Act: 2.7180. Min Act: -0.0000

Data Index: 526027 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.7448. Min Act: -0.0000

Data Index: 1097611 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.7762. Min Act: -0.0000

Data Index: 398993 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.5049. Min Act: -0.0000

Data Index: 173069 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.5351. Min Act: -0.0000

Data Index: 435063 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1086006 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.4032. Min Act: -0.0000

Data Index: 468596 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.3538. Min Act: -0.0000

Data Index: 569462 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.1983. Min Act: -0.0000

Data Index: 708866 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1345265 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1297033 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.0938. Min Act: -0.0000

Data Index: 448174 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 2.7180. Min Range: -2.7180

Max Act: 1.0415. Min Act: -0.0000

Data Index: 492077 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1138410 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.9637. Min Act: -0.0000

Data Index: 137955 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.8790. Min Act: -0.0000

Data Index: 578376 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.9130. Min Act: -0.0000

Data Index: 634817 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1065712 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.8924. Min Act: -0.0000

Data Index: 256251 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.7180. Min Range: -2.7180

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1148764 (C4 (Web Text))

Max Activating Token Index: 899