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

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

Neuron 1757 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: 6.1436. Min Range: -6.1436

Max Act: 6.1436. Min Act: -0.1700

Data Index: 1608345 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.8623. Min Act: -0.1700

Data Index: 1646118 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.8311. Min Act: -0.1700

Data Index: 1388340 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.7686. Min Act: -0.1700

Data Index: 1523577 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.6748. Min Act: -0.1700

Data Index: 1428933 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.6123. Min Act: -0.1700

Data Index: 1656827 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.6123. Min Act: -0.1700

Data Index: 1510085 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.5811. Min Act: -0.1700

Data Index: 1408533 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.6123. Min Act: -0.1700

Data Index: 1432171 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.5498. Min Act: -0.1700

Data Index: 1480502 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.5186. Min Act: -0.1700

Data Index: 1417684 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.5186. Min Act: -0.1700

Data Index: 1650966 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.4561. Min Act: -0.1700

Data Index: 1430632 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.4873. Min Act: -0.1700

Data Index: 1463106 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.4248. Min Act: -0.1700

Data Index: 1634809 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.3936. Min Act: -0.1700

Data Index: 1615101 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.3936. Min Act: -0.1700

Data Index: 1539374 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.3623. Min Act: -0.1699

Data Index: 1511200 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.3311. Min Act: -0.1700

Data Index: 1460434 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 6.1436. Min Range: -6.1436

Max Act: 5.3311. Min Act: -0.1700

Data Index: 1507090 (Python Code)

Max Activating Token Index: 1023