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

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

Neuron 5032 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0932. Min Range: -1.0932

Max Act: 1.0932. Min Act: -0.0000

Data Index: 277817 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1145938 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.7578. Min Act: -0.0000

Data Index: 237666 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1183304 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.7085. Min Act: -0.0000

Data Index: 960726 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6054. Min Act: -0.0000

Data Index: 19336 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6330. Min Act: -0.0000

Data Index: 39727 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6591. Min Act: -0.0000

Data Index: 77973 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6131. Min Act: -0.0000

Data Index: 210810 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6213. Min Act: -0.0000

Data Index: 628389 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.6241. Min Act: -0.0000

Data Index: 141097 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5565. Min Act: -0.0000

Data Index: 579692 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5171. Min Act: -0.0000

Data Index: 927248 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5998. Min Act: -0.0000

Data Index: 923204 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5458. Min Act: -0.0000

Data Index: 226231 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1186089 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5550. Min Act: -0.0000

Data Index: 503888 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5408. Min Act: -0.0000

Data Index: 772960 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.0932. Min Range: -1.0932

Max Act: 0.5040. Min Act: -0.0000

Data Index: 511672 (C4 (Web Text))

Max Activating Token Index: 614