Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 823 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.6429. Min Act: -0.1700

Data Index: 1377577 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.6429. Min Act: -0.1700

Data Index: 1411293 (Python Code)

Max Activating Token Index: 353

Text #2

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.5179. Min Act: -0.1700

Data Index: 1641144 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.5179. Min Act: -0.1700

Data Index: 1583888 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.4554. Min Act: -0.1700

Data Index: 1619700 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3304. Min Act: -0.1700

Data Index: 1606599 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.4866. Min Act: -0.1700

Data Index: 1407441 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3616. Min Act: -0.1700

Data Index: 1554382 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3616. Min Act: -0.1700

Data Index: 1428493 (Python Code)

Max Activating Token Index: 529

Text #9

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2679. Min Act: -0.1700

Data Index: 1540235 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3929. Min Act: -0.1700

Data Index: 1398353 (Python Code)

Max Activating Token Index: 848

Text #11

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3616. Min Act: -0.1700

Data Index: 1399677 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3616. Min Act: -0.1700

Data Index: 1367428 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3304. Min Act: -0.1700

Data Index: 1441318 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2991. Min Act: -0.1700

Data Index: 1512887 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2991. Min Act: -0.1700

Data Index: 1622257 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.3304. Min Act: -0.1700

Data Index: 1518841 (Python Code)

Max Activating Token Index: 526

Text #17

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2991. Min Act: -0.1700

Data Index: 1578803 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2366. Min Act: -0.1700

Data Index: 1582701 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 5.6429. Min Range: -5.6429

Max Act: 5.2991. Min Act: -0.1700

Data Index: 1580121 (Python Code)

Max Activating Token Index: 889