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

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

Neuron 4018 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: 0.9991. Min Range: -0.9991

Max Act: 0.9991. Min Act: -0.0000

Data Index: 584640 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.9928. Min Act: -0.0000

Data Index: 230735 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8557. Min Act: -0.0000

Data Index: 372628 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8439. Min Act: -0.0000

Data Index: 789575 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8083. Min Act: -0.0000

Data Index: 436358 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7885. Min Act: 0.0000

Data Index: 213698 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8068. Min Act: -0.0000

Data Index: 694770 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1109836 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7509. Min Act: -0.0000

Data Index: 983479 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1105462 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.8104. Min Act: -0.0000

Data Index: 614787 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7287. Min Act: -0.0000

Data Index: 633798 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7444. Min Act: -0.0000

Data Index: 398462 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7367. Min Act: -0.0000

Data Index: 924411 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7368. Min Act: 0.0000

Data Index: 809064 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7584. Min Act: 0.0000

Data Index: 198809 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7069. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1085907 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.7235. Min Act: -0.0000

Data Index: 199443 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.9991. Min Range: -0.9991

Max Act: 0.6428. Min Act: -0.0000

Data Index: 33739 (C4 (Web Text))

Max Activating Token Index: 361