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

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

Neuron 363 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: 0.9772. Min Range: -0.9772

Max Act: 0.9772. Min Act: -0.0001

Data Index: 269400 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9148. Min Act: -0.0001

Data Index: 767458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9105. Min Act: -0.0001

Data Index: 1254805 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8963. Min Act: -0.0001

Data Index: 563687 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8812. Min Act: -0.0001

Data Index: 1283949 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8503. Min Act: -0.0001

Data Index: 1119909 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8568. Min Act: -0.0001

Data Index: 5579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1038191 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8484. Min Act: -0.0001

Data Index: 364840 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8389. Min Act: -0.0001

Data Index: 155131 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8496. Min Act: -0.0001

Data Index: 665098 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8416. Min Act: -0.0001

Data Index: 861502 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8389. Min Act: -0.0001

Data Index: 257214 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8314. Min Act: -0.0001

Data Index: 21610 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1230578 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8338. Min Act: -0.0001

Data Index: 668875 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8293. Min Act: -0.0001

Data Index: 705752 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8227. Min Act: -0.0001

Data Index: 761057 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1207256 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8113. Min Act: -0.0001

Data Index: 614917 (C4 (Web Text))

Max Activating Token Index: 111