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

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

Neuron 214 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.3339. Min Act: -0.1700

Data Index: 1586480 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.3025. Min Act: -0.1700

Data Index: 170496 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.3025. Min Act: -0.1700

Data Index: 1568962 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2710. Min Act: -0.1700

Data Index: 562078 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2710. Min Act: -0.1700

Data Index: 1627265 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1317998 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1603658 (Python Code)

Max Activating Token Index: 742

Text #7

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1415745 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1384275 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2081. Min Act: -0.1700

Data Index: 1363340 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2081. Min Act: -0.1700

Data Index: 1417597 (Python Code)

Max Activating Token Index: 404

Text #11

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1514123 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 142404 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1630427 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1529468 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1581891 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.2081. Min Act: -0.1700

Data Index: 900844 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1452. Min Act: -0.1700

Data Index: 469653 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1424509 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 3.3339. Min Range: -3.3339

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1377483 (Python Code)

Max Activating Token Index: 958