Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 41 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8764. Min Act: -0.1700

Data Index: 368812 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8138. Min Act: -0.1700

Data Index: 569215 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8451. Min Act: -0.1700

Data Index: 163189 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7200. Min Act: -0.1700

Data Index: 778621 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8138. Min Act: -0.1700

Data Index: 208049 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8138. Min Act: -0.1700

Data Index: 49506 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7825. Min Act: -0.1700

Data Index: 961203 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7513. Min Act: -0.1700

Data Index: 32135 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7825. Min Act: -0.1700

Data Index: 51459 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7825. Min Act: -0.1700

Data Index: 780296 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7513. Min Act: -0.1700

Data Index: 969863 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.8138. Min Act: -0.1700

Data Index: 80734 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.7200. Min Act: -0.1700

Data Index: 999417 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6887. Min Act: -0.1700

Data Index: 541146 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6887. Min Act: -0.1700

Data Index: 706956 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6887. Min Act: -0.1700

Data Index: 706093 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6574. Min Act: -0.1700

Data Index: 981442 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6574. Min Act: -0.1700

Data Index: 1436030 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6574. Min Act: -0.1700

Data Index: 544325 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 3.8764. Min Range: -3.8764

Max Act: 3.6574. Min Act: -0.1700

Data Index: 353363 (C4 (Web Text))

Max Activating Token Index: 683