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

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

Neuron 3768 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: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0001

Data Index: 858447 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0390. Min Act: -0.0001

Data Index: 275618 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0376. Min Act: -0.0001

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0374. Min Act: -0.0001

Data Index: 227707 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0377. Min Act: -0.0002

Data Index: 144928 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0380. Min Act: -0.0001

Data Index: 954990 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1041648 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0374. Min Act: -0.0001

Data Index: 504130 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1224012 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0365. Min Act: -0.0001

Data Index: 981175 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0368. Min Act: -0.0001

Data Index: 213758 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0366. Min Act: -0.0001

Data Index: 564085 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0367. Min Act: -0.0001

Data Index: 57294 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0360. Min Act: -0.0001

Data Index: 125736 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0369. Min Act: -0.0001

Data Index: 25811 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1312513 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0360. Min Act: -0.0001

Data Index: 471231 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1358673 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0360. Min Act: -0.0001

Data Index: 191549 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1093913 (C4 (Web Text))

Max Activating Token Index: 47