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

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

Neuron 1412 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.4620. Min Act: -0.1700

Data Index: 1525014 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.2422. Min Act: -0.1700

Data Index: 1495099 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1589859 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.2422. Min Act: -0.1700

Data Index: 1439830 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.2108. Min Act: -0.1700

Data Index: 468447 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1555894 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.1163. Min Act: -0.1700

Data Index: 1635063 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.1321. Min Act: -0.1700

Data Index: 1430594 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.1163. Min Act: -0.1700

Data Index: 1445951 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1636734 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0848. Min Act: -0.1700

Data Index: 244957 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1474548 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1616839 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0216. Min Act: -0.1700

Data Index: 1529117 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0216. Min Act: -0.1700

Data Index: 1541583 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1609503 (Python Code)

Max Activating Token Index: 342

Text #16

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1435770 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1420271 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0058. Min Act: -0.1700

Data Index: 1453632 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 3.4620. Min Range: -3.4620

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1474371 (Python Code)

Max Activating Token Index: 731