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

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

Neuron 430 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: 5.3038. Min Range: -5.3038

Max Act: 5.2725. Min Act: -0.1700

Data Index: 1534328 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.3038. Min Act: -0.1700

Data Index: 1539959 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.2725. Min Act: -0.1700

Data Index: 1516156 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.1475. Min Act: -0.1700

Data Index: 1582038 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.1163. Min Act: -0.1700

Data Index: 1479962 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.1788. Min Act: -0.1700

Data Index: 1611417 (Python Code)

Max Activating Token Index: 675

Text #6

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1468053 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1577295 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.1163. Min Act: -0.1700

Data Index: 1543573 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1423542 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1564594 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1533817 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1419221 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9600. Min Act: -0.1700

Data Index: 1626730 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1466526 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1549992 (Python Code)

Max Activating Token Index: 388

Text #16

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1589975 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9600. Min Act: -0.1700

Data Index: 1421813 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 5.3038. Min Range: -5.3038

Max Act: 5.0538. Min Act: -0.1700

Data Index: 1578312 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 5.3038. Min Range: -5.3038

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1519569 (Python Code)

Max Activating Token Index: 454