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

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

Neuron 1496 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: 0.6143. Min Range: -0.6143

Max Act: 0.6143. Min Act: -0.0002

Data Index: 600080 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5985. Min Act: -0.0002

Data Index: 1281551 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5889. Min Act: -0.0001

Data Index: 268092 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5639. Min Act: -0.0001

Data Index: 513334 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5716. Min Act: -0.0001

Data Index: 558867 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1116479 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5565. Min Act: -0.0001

Data Index: 197986 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5484. Min Act: -0.0001

Data Index: 815782 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5622. Min Act: -0.0001

Data Index: 729183 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5430. Min Act: -0.0001

Data Index: 757886 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5427. Min Act: -0.0001

Data Index: 1143625 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1090920 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5306. Min Act: -0.0001

Data Index: 406959 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1224970 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5458. Min Act: -0.0001

Data Index: 108411 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5277. Min Act: -0.0001

Data Index: 647631 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5306. Min Act: -0.0001

Data Index: 711488 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5184. Min Act: -0.0001

Data Index: 1194100 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5200. Min Act: -0.0001

Data Index: 267892 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5197. Min Act: -0.0001

Data Index: 747630 (C4 (Web Text))

Max Activating Token Index: 538