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

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

Neuron 1217 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.7005. Min Act: -0.1700

Data Index: 126354 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.6067. Min Act: -0.1700

Data Index: 478113 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4505. Min Act: -0.1700

Data Index: 136539 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4817. Min Act: -0.1700

Data Index: 978503 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4505. Min Act: -0.1700

Data Index: 378444 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4817. Min Act: -0.1700

Data Index: 1048512 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.3880. Min Act: -0.1700

Data Index: 1231618 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4192. Min Act: -0.1700

Data Index: 35042 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.4505. Min Act: -0.1700

Data Index: 293993 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.3567. Min Act: -0.1700

Data Index: 702646 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.3880. Min Act: -0.1700

Data Index: 175862 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.3255. Min Act: -0.1700

Data Index: 571690 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.3880. Min Act: -0.1700

Data Index: 378055 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1700

Data Index: 745518 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1700

Data Index: 65490 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1700

Data Index: 1202923 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1700

Data Index: 585129 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1700

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.1692. Min Act: -0.1700

Data Index: 1181184 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 5.7005. Min Range: -5.7005

Max Act: 5.2942. Min Act: -0.1699

Data Index: 384375 (C4 (Web Text))

Max Activating Token Index: 177