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

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

Neuron 2023 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: 3.1692. Min Range: -3.1692

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1228784 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1692. Min Act: -0.1700

Data Index: 422022 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1535. Min Act: -0.1700

Data Index: 320522 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1068720 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1189103 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1069936 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1295551 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1220. Min Act: -0.1700

Data Index: 395127 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 234331 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1224722 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 546373 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 456940 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1220. Min Act: -0.1700

Data Index: 926335 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 153726 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1167177 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 141706 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1321543 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.0905. Min Act: -0.1700

Data Index: 156316 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.0905. Min Act: -0.1700

Data Index: 885844 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 3.1692. Min Range: -3.1692

Max Act: 3.0905. Min Act: -0.1700

Data Index: 449801 (C4 (Web Text))

Max Activating Token Index: 1023