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

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

Neuron 1632 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: 3.8716. Min Range: -3.8716

Max Act: 3.8560. Min Act: -0.1700

Data Index: 1182055 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.8716. Min Act: -0.1700

Data Index: 785180 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7778. Min Act: -0.1700

Data Index: 721992 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7621. Min Act: -0.1700

Data Index: 503814 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7621. Min Act: -0.1700

Data Index: 858518 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7621. Min Act: -0.1700

Data Index: 44711 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6056. Min Act: -0.1700

Data Index: 64797 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5900. Min Act: -0.1700

Data Index: 614 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6682. Min Act: -0.1700

Data Index: 1320624 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6526. Min Act: -0.1700

Data Index: 1220009 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6526. Min Act: -0.1700

Data Index: 393210 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6526. Min Act: -0.1700

Data Index: 665431 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6213. Min Act: -0.1700

Data Index: 540018 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5743. Min Act: -0.1700

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5743. Min Act: -0.1700

Data Index: 907704 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6056. Min Act: -0.1700

Data Index: 204738 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5430. Min Act: -0.1700

Data Index: 719744 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5430. Min Act: -0.1700

Data Index: 240724 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5430. Min Act: -0.1700

Data Index: 947493 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.5743. Min Act: -0.1700

Data Index: 301645 (C4 (Web Text))

Max Activating Token Index: 277