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

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

Neuron 1581 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.4618. Min Act: -0.1700

Data Index: 615915 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.3834. Min Act: -0.1700

Data Index: 225693 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.3363. Min Act: -0.1700

Data Index: 1261039 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.3520. Min Act: -0.1700

Data Index: 1283757 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.3049. Min Act: -0.1700

Data Index: 687709 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.3049. Min Act: -0.1700

Data Index: 363611 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2735. Min Act: -0.1700

Data Index: 1197446 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2578. Min Act: -0.1700

Data Index: 649444 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2578. Min Act: -0.1700

Data Index: 132356 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2578. Min Act: -0.1700

Data Index: 789922 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2421. Min Act: -0.1700

Data Index: 978102 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2421. Min Act: -0.1700

Data Index: 220766 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2106. Min Act: -0.1700

Data Index: 992007 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.2106. Min Act: -0.1700

Data Index: 651192 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1949. Min Act: -0.1700

Data Index: 103956 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1634. Min Act: -0.1700

Data Index: 413814 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1634. Min Act: -0.1700

Data Index: 107542 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1634. Min Act: -0.1700

Data Index: 151017 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1477. Min Act: -0.1700

Data Index: 1205071 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.4618. Min Range: -3.4618

Max Act: 3.1477. Min Act: -0.1700

Data Index: 392737 (C4 (Web Text))

Max Activating Token Index: 677