Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2024 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1732. Min Act: 0.2804

Data Index: 1461094 (Python Code)

Max Activating Token Index: 545

Text #1

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1669. Min Act: -0.1398

Data Index: 1369268 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1425. Min Act: -0.0449

Data Index: 1626226 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1519. Min Act: 0.3035

Data Index: 1649936 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1214. Min Act: -0.1700

Data Index: 1555051 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0833. Min Act: -0.1695

Data Index: 1580960 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0924. Min Act: 0.0223

Data Index: 1547366 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.1009. Min Act: -0.1699

Data Index: 1368326 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0545. Min Act: -0.1700

Data Index: 1553030 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0469. Min Act: 0.2826

Data Index: 1637079 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0528. Min Act: -0.1693

Data Index: 1447639 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0652. Min Act: 0.1869

Data Index: 1590928 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0434. Min Act: 0.0251

Data Index: 1602257 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0429. Min Act: 0.5119

Data Index: 1486944 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0411. Min Act: 0.4434

Data Index: 1380885 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0204. Min Act: -0.1091

Data Index: 1543078 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0274. Min Act: -0.1697

Data Index: 1544741 (Python Code)

Max Activating Token Index: 662

Text #17

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0208. Min Act: 0.7854

Data Index: 1491279 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0202. Min Act: 0.7444

Data Index: 1629820 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 4.1732. Min Range: -4.1732

Max Act: 4.0256. Min Act: -0.1700

Data Index: 1489499 (Python Code)

Max Activating Token Index: 725