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

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

Neuron 1446 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.4487. Min Act: -0.1700

Data Index: 918705 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.2289. Min Act: -0.1700

Data Index: 172276 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.2132. Min Act: -0.1700

Data Index: 1251021 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1817. Min Act: -0.1700

Data Index: 410809 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1345. Min Act: -0.1700

Data Index: 862911 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1345. Min Act: -0.1700

Data Index: 635816 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1187. Min Act: -0.1700

Data Index: 979367 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1076998 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1345. Min Act: -0.1700

Data Index: 975280 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1276370 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1030. Min Act: -0.1700

Data Index: 663514 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1187. Min Act: -0.1700

Data Index: 557561 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1327398 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.0872. Min Act: -0.1700

Data Index: 1113400 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1030. Min Act: -0.1700

Data Index: 1162104 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1030. Min Act: -0.1700

Data Index: 742118 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.1030. Min Act: -0.1700

Data Index: 8827 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.0872. Min Act: -0.1700

Data Index: 1207726 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.0872. Min Act: -0.1700

Data Index: 1087687 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 3.4487. Min Range: -3.4487

Max Act: 3.0714. Min Act: -0.1700

Data Index: 523511 (C4 (Web Text))

Max Activating Token Index: 195