Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1905 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.7317. Min Act: -0.1700

Data Index: 1530476 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.7317. Min Act: -0.1700

Data Index: 1609697 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1473653 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1460162 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6848. Min Act: -0.1700

Data Index: 1459183 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6691. Min Act: -0.1700

Data Index: 1584883 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6535. Min Act: -0.1700

Data Index: 1643812 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6378. Min Act: -0.1700

Data Index: 1650331 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1496456 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1383785 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6222. Min Act: -0.1700

Data Index: 1472128 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1404460 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1366282 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5908. Min Act: -0.1700

Data Index: 1540010 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1476697 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1522335 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1404135 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1580424 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1383953 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 3.7317. Min Range: -3.7317

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1573711 (Python Code)

Max Activating Token Index: 606