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

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

Neuron 1682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.3149. Min Act: -0.1700

Data Index: 1492232 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.2524. Min Act: -0.1700

Data Index: 1480338 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.1899. Min Act: -0.1700

Data Index: 1561416 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.1586. Min Act: -0.1700

Data Index: 1651711 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0961. Min Act: -0.1700

Data Index: 1543253 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0961. Min Act: -0.1700

Data Index: 1608651 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0649. Min Act: -0.1700

Data Index: 1583745 (Python Code)

Max Activating Token Index: 627

Text #7

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0649. Min Act: -0.1700

Data Index: 1453519 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0649. Min Act: -0.1700

Data Index: 1547773 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0336. Min Act: -0.1700

Data Index: 1515720 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0336. Min Act: -0.1700

Data Index: 1374291 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0024. Min Act: -0.1700

Data Index: 1595801 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0024. Min Act: -0.1700

Data Index: 1558861 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1561363 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 5.3149. Min Range: -5.3149

Max Act: 5.0024. Min Act: -0.1700

Data Index: 1505558 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1611093 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9086. Min Act: -0.1700

Data Index: 1606791 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1593201 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1395378 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 5.3149. Min Range: -5.3149

Max Act: 4.9399. Min Act: -0.1700

Data Index: 1544099 (Python Code)

Max Activating Token Index: 63