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

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

Neuron 5433 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.1843. Min Act: -0.0001

Data Index: 601020 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.1058. Min Act: -0.0001

Data Index: 1111523 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0864. Min Act: -0.0001

Data Index: 58381 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0278. Min Act: -0.0001

Data Index: 57846 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0278. Min Act: -0.0001

Data Index: 71574 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0273. Min Act: -0.0001

Data Index: 1195056 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0005. Min Act: -0.0001

Data Index: 1269718 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9609. Min Act: -0.0001

Data Index: 247204 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9421. Min Act: -0.0001

Data Index: 996120 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9504. Min Act: -0.0001

Data Index: 875162 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9490. Min Act: -0.0001

Data Index: 808140 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9348. Min Act: -0.0001

Data Index: 369925 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1330160 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9171. Min Act: -0.0001

Data Index: 606124 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9159. Min Act: -0.0001

Data Index: 353606 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1356712 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9098. Min Act: -0.0001

Data Index: 892781 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8899. Min Act: -0.0002

Data Index: 1334432 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9013. Min Act: -0.0001

Data Index: 424581 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9175. Min Act: -0.0001

Data Index: 473916 (C4 (Web Text))

Max Activating Token Index: 6