Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4204. Min Act: -0.0001

Data Index: 579551 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3604. Min Act: -0.0001

Data Index: 237002 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3870. Min Act: -0.0001

Data Index: 159483 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3749. Min Act: -0.0001

Data Index: 1356432 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3564. Min Act: -0.0001

Data Index: 251899 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3328. Min Act: -0.0001

Data Index: 945261 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3408. Min Act: -0.0001

Data Index: 236962 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3201. Min Act: -0.0001

Data Index: 536794 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3412. Min Act: -0.0001

Data Index: 1222002 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3568. Min Act: -0.0001

Data Index: 746691 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3254. Min Act: -0.0001

Data Index: 861169 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3107. Min Act: -0.0001

Data Index: 442297 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1008366 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3269. Min Act: -0.0001

Data Index: 325015 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3127. Min Act: -0.0001

Data Index: 87547 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1244055 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3030. Min Act: -0.0001

Data Index: 208448 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3119. Min Act: -0.0001

Data Index: 482440 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3080. Min Act: -0.0001

Data Index: 689270 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3033. Min Act: -0.0001

Data Index: 27342 (C4 (Web Text))

Max Activating Token Index: 562