Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1706 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.4838. Min Act: -0.1700

Data Index: 626974 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.4211. Min Act: -0.1700

Data Index: 45753 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.4211. Min Act: -0.1700

Data Index: 694181 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.4367. Min Act: -0.1700

Data Index: 89715 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 986801 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.4054. Min Act: -0.1700

Data Index: 578774 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 197011 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 1143281 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 759607 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 779384 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3740. Min Act: -0.1700

Data Index: 79504 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3583. Min Act: -0.1700

Data Index: 185366 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 272305 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 467312 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 1113760 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 430585 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 585400 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3426. Min Act: -0.1700

Data Index: 1187215 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3269. Min Act: -0.1700

Data Index: 13580 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.4838. Min Range: -3.4838

Max Act: 3.3112. Min Act: -0.1700

Data Index: 544748 (C4 (Web Text))

Max Activating Token Index: 570