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

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

Neuron 957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.5025. Min Act: -0.1700

Data Index: 804630 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.4868. Min Act: -0.1700

Data Index: 743172 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.4555. Min Act: -0.1700

Data Index: 720553 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.4555. Min Act: -0.1700

Data Index: 646940 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3928. Min Act: -0.1700

Data Index: 103753 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.4084. Min Act: -0.1700

Data Index: 1255969 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3771. Min Act: -0.1700

Data Index: 971607 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3771. Min Act: -0.1700

Data Index: 306622 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3614. Min Act: -0.1700

Data Index: 473944 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3457. Min Act: -0.1700

Data Index: 1241088 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3771. Min Act: -0.1700

Data Index: 925706 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3457. Min Act: -0.1700

Data Index: 314156 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3300. Min Act: -0.1700

Data Index: 265044 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3300. Min Act: -0.1700

Data Index: 1286810 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3457. Min Act: -0.1700

Data Index: 978653 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3143. Min Act: -0.1700

Data Index: 1144365 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.2986. Min Act: -0.1700

Data Index: 1318204 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.3143. Min Act: -0.1700

Data Index: 1293388 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.2986. Min Act: -0.1700

Data Index: 77774 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 3.5025. Min Range: -3.5025

Max Act: 3.2829. Min Act: -0.1700

Data Index: 227542 (C4 (Web Text))

Max Activating Token Index: 533