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

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

Neuron 1497 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: 3.9380. Min Range: -3.9380

Max Act: 3.9380. Min Act: -0.1700

Data Index: 1463339 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8755. Min Act: -0.1700

Data Index: 1446784 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8755. Min Act: -0.1700

Data Index: 1644850 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8442. Min Act: -0.1700

Data Index: 1563949 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8129. Min Act: -0.1700

Data Index: 1613871 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8442. Min Act: -0.1700

Data Index: 1549419 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7816. Min Act: -0.1700

Data Index: 1406913 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.8129. Min Act: -0.1700

Data Index: 1403404 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7503. Min Act: -0.1699

Data Index: 765343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7503. Min Act: -0.1700

Data Index: 1491071 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7190. Min Act: -0.1700

Data Index: 1519151 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7034. Min Act: -0.1700

Data Index: 1491604 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7503. Min Act: -0.1700

Data Index: 1409004 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7503. Min Act: -0.1700

Data Index: 1504617 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7034. Min Act: -0.1700

Data Index: 1445628 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1652694 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.7034. Min Act: -0.1699

Data Index: 1500598 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1587955 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1528093 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.9380. Min Range: -3.9380

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1596501 (Python Code)

Max Activating Token Index: 1023