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

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

Neuron 1313 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: 6.3737. Min Range: -6.3737

Max Act: 6.3425. Min Act: -0.1700

Data Index: 1420022 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.3737. Min Act: -0.1700

Data Index: 1417819 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.3425. Min Act: -0.1700

Data Index: 1531877 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.2175. Min Act: -0.1700

Data Index: 1439052 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.1862. Min Act: -0.1700

Data Index: 1574972 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.2487. Min Act: -0.1700

Data Index: 1517422 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.1550. Min Act: -0.1700

Data Index: 1463638 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.1550. Min Act: -0.1700

Data Index: 1529919 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.0925. Min Act: -0.1700

Data Index: 1635343 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.0612. Min Act: -0.1700

Data Index: 1500746 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.1237. Min Act: -0.1700

Data Index: 471100 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.0612. Min Act: -0.1700

Data Index: 1553320 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9675. Min Act: -0.1700

Data Index: 1367823 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.0300. Min Act: -0.1700

Data Index: 1629473 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 6.3737. Min Range: -6.3737

Max Act: 6.0300. Min Act: -0.1700

Data Index: 1598626 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9362. Min Act: -0.1700

Data Index: 1607319 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9675. Min Act: -0.1700

Data Index: 1459201 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9362. Min Act: -0.1700

Data Index: 1629273 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9050. Min Act: -0.1700

Data Index: 1410442 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 6.3737. Min Range: -6.3737

Max Act: 5.9362. Min Act: -0.1700

Data Index: 1540643 (Python Code)

Max Activating Token Index: 886