Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1071 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1364391 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2971. Min Act: -0.1700

Data Index: 976995 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1468081 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1596626 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2185. Min Act: -0.1700

Data Index: 86054 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1375951 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1564865 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0767. Min Act: -0.1700

Data Index: 1489165 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1398. Min Act: -0.1700

Data Index: 830383 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0767. Min Act: -0.1700

Data Index: 837534 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0767. Min Act: -0.1700

Data Index: 565051 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0925. Min Act: -0.1700

Data Index: 707825 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0767. Min Act: -0.1700

Data Index: 822226 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0610. Min Act: -0.1700

Data Index: 1622548 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0610. Min Act: -0.1700

Data Index: 961109 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0610. Min Act: -0.1700

Data Index: 1292712 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0452. Min Act: -0.1700

Data Index: 1560977 (Python Code)

Max Activating Token Index: 471

Text #17

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1370523 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0294. Min Act: -0.1700

Data Index: 660417 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0136. Min Act: -0.1700

Data Index: 1455167 (Python Code)

Max Activating Token Index: 218