Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 882 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1166085 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.7215. Min Act: -0.1700

Data Index: 1250116 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.7361. Min Act: -0.1700

Data Index: 168308 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.7130. Min Act: -0.1700

Data Index: 1304770 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.6922. Min Act: -0.1700

Data Index: 402087 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.6666. Min Act: -0.1700

Data Index: 786887 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5931. Min Act: -0.1700

Data Index: 1032567 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.6197. Min Act: -0.1700

Data Index: 163324 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.6084. Min Act: -0.1700

Data Index: 431396 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5742. Min Act: -0.1700

Data Index: 846631 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5826. Min Act: -0.1700

Data Index: 561381 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5675. Min Act: -0.1700

Data Index: 630485 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5608. Min Act: -0.1700

Data Index: 451406 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5315. Min Act: -0.1700

Data Index: 219047 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5430. Min Act: -0.1700

Data Index: 25459 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5466. Min Act: -0.1700

Data Index: 530356 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5469. Min Act: -0.1700

Data Index: 900446 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5475. Min Act: -0.1700

Data Index: 91908 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5602. Min Act: -0.1700

Data Index: 920737 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5462. Min Act: -0.1700

Data Index: 986529 (C4 (Web Text))

Max Activating Token Index: 809