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

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

Neuron 4634 in Layer 1

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: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 566198 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1161061 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0448. Min Act: -0.0002

Data Index: 922916 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1282909 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0439. Min Act: -0.0002

Data Index: 893692 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1131774 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0431. Min Act: -0.0002

Data Index: 119648 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1148024 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1068896 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0398. Min Act: -0.0002

Data Index: 73723 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0400. Min Act: -0.0002

Data Index: 455481 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0394. Min Act: -0.0002

Data Index: 993974 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0396. Min Act: -0.0002

Data Index: 191291 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1575017 (Python Code)

Max Activating Token Index: 518

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0002

Data Index: 995955 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0377. Min Act: -0.0002

Data Index: 704929 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1527657 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1308059 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1071997 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1129622 (C4 (Web Text))

Max Activating Token Index: 607