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

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

Neuron 488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.9957. Min Act: -0.0000

Data Index: 1339872 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.9060. Min Act: -0.0000

Data Index: 1234329 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.3400. Min Act: -0.0000

Data Index: 187619 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2281. Min Act: -0.0000

Data Index: 873917 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.3602. Min Act: -0.0000

Data Index: 750084 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.4784. Min Act: -0.0000

Data Index: 1159343 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.3201. Min Act: -0.0000

Data Index: 6804 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2857. Min Act: -0.0000

Data Index: 99569 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2767. Min Act: -0.0000

Data Index: 997072 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 4.9957. Min Range: -4.9957

Max Act: 3.7515. Min Act: -0.0000

Data Index: 580683 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2597. Min Act: -0.0001

Data Index: 824860 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2434. Min Act: -0.0000

Data Index: 1354245 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2340. Min Act: -0.0000

Data Index: 1244488 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.0495. Min Act: -0.0000

Data Index: 111982 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.1593. Min Act: -0.0000

Data Index: 765918 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.1473. Min Act: -0.0000

Data Index: 1301911 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2946. Min Act: -0.0000

Data Index: 13311 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.1013. Min Act: -0.0000

Data Index: 82053 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 4.9957. Min Range: -4.9957

Max Act: 3.9361. Min Act: -0.0000

Data Index: 577148 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 4.9957. Min Range: -4.9957

Max Act: 4.2824. Min Act: -0.0000

Data Index: 461725 (C4 (Web Text))

Max Activating Token Index: 228