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

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

Neuron 460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.3824. Min Act: -0.1700

Data Index: 1541905 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1502778 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1434523 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1461233 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2725. Min Act: -0.1700

Data Index: 1543218 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2725. Min Act: -0.1700

Data Index: 1472913 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1499200 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2568. Min Act: -0.1700

Data Index: 1602996 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2411. Min Act: -0.1700

Data Index: 1439162 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1638159 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1644932 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1462853 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1515488 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1569926 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1559400 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1375701 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1482595 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1579645 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.1939. Min Act: -0.1700

Data Index: 1533508 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 3.4138. Min Range: -3.4138

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1552004 (Python Code)

Max Activating Token Index: 664