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

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

Neuron 525 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: 3.8500. Min Range: -3.8500

Max Act: 3.8500. Min Act: -0.1700

Data Index: 1466279 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7562. Min Act: -0.1700

Data Index: 1596005 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.5213. Min Act: -0.1700

Data Index: 1470243 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1640068 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3803. Min Act: -0.1700

Data Index: 1546870 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.4430. Min Act: -0.1700

Data Index: 1569143 (Python Code)

Max Activating Token Index: 105

Text #6

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3803. Min Act: -0.1700

Data Index: 1466867 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1395405 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1372373 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1516341 (Python Code)

Max Activating Token Index: 786

Text #10

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1629408 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1597556 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1537379 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2704. Min Act: -0.1700

Data Index: 1422005 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1504581 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2546. Min Act: -0.1700

Data Index: 1512950 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2704. Min Act: -0.1699

Data Index: 1425760 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1488416 (Python Code)

Max Activating Token Index: 615

Text #18

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2232. Min Act: -0.1700

Data Index: 1649323 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1577716 (Python Code)

Max Activating Token Index: 309