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

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

Neuron 319 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: 0.3687. Min Range: -0.3687

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1426526 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1476535 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3433. Min Act: -0.0001

Data Index: 1369692 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1461123 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1384299 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3264. Min Act: -0.0002

Data Index: 1501567 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1452466 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3316. Min Act: -0.0002

Data Index: 1450866 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3264. Min Act: -0.0002

Data Index: 1603350 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3245. Min Act: -0.0002

Data Index: 1569662 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3237. Min Act: -0.0001

Data Index: 1461730 (Python Code)

Max Activating Token Index: 337

Text #11

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1400790 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3148. Min Act: -0.0001

Data Index: 1514636 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3215. Min Act: -0.0002

Data Index: 1586386 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1529934 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3117. Min Act: -0.0002

Data Index: 1463283 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3081. Min Act: -0.0001

Data Index: 1561712 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1492778 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3162. Min Act: -0.0001

Data Index: 1618744 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1640863 (Python Code)

Max Activating Token Index: 417