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

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

Neuron 1496 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: 7.3904. Min Range: -7.3904

Max Act: 7.3904. Min Act: -0.1694

Data Index: 1240073 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 7.3904. Min Range: -7.3904

Max Act: 7.0154. Min Act: -0.1697

Data Index: 183994 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.8279. Min Act: -0.1695

Data Index: 1018772 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.9529. Min Act: -0.1700

Data Index: 713985 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.8904. Min Act: -0.1697

Data Index: 1108991 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.7029. Min Act: -0.1700

Data Index: 620936 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5779. Min Act: -0.1695

Data Index: 459252 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6404. Min Act: -0.1694

Data Index: 1304601 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5779. Min Act: -0.1700

Data Index: 928527 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6404. Min Act: -0.1699

Data Index: 459932 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6404. Min Act: -0.1700

Data Index: 920476 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5154. Min Act: -0.1700

Data Index: 719444 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.4529. Min Act: -0.1699

Data Index: 1300048 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5779. Min Act: -0.1700

Data Index: 1106188 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6404. Min Act: -0.1700

Data Index: 984803 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5154. Min Act: -0.1700

Data Index: 534283 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6404. Min Act: -0.1676

Data Index: 1008511 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.4529. Min Act: -0.1700

Data Index: 608059 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.3904. Min Act: -0.1698

Data Index: 824493 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.3279. Min Act: -0.1700

Data Index: 281358 (C4 (Web Text))

Max Activating Token Index: 829