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

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

Neuron 986 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: 3.2512. Min Range: -3.2512

Max Act: 3.2512. Min Act: -0.1700

Data Index: 1472286 (Python Code)

Max Activating Token Index: 922

Text #1

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1414827 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.2040. Min Act: -0.1700

Data Index: 1469402 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1580164 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1410. Min Act: -0.1700

Data Index: 1457796 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1551818 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1377749 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1253. Min Act: -0.1700

Data Index: 1586447 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0622. Min Act: -0.1700

Data Index: 1511103 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0780. Min Act: -0.1700

Data Index: 1477648 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1379108 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0622. Min Act: -0.1700

Data Index: 1656394 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1574885 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0780. Min Act: -0.1700

Data Index: 1478452 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0780. Min Act: -0.1700

Data Index: 1416500 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0464. Min Act: -0.1700

Data Index: 1616744 (Python Code)

Max Activating Token Index: 909

Text #16

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0622. Min Act: -0.1700

Data Index: 1603155 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0148. Min Act: -0.1700

Data Index: 1489733 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0148. Min Act: -0.1700

Data Index: 1366341 (Python Code)

Max Activating Token Index: 277

Text #19

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1503031 (Python Code)

Max Activating Token Index: 412