Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1066 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.7844. Min Act: -0.1700

Data Index: 1331554 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.5966. Min Act: -0.1700

Data Index: 1318253 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.4556. Min Act: -0.1700

Data Index: 116691 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.4556. Min Act: -0.1700

Data Index: 758961 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.3615. Min Act: -0.1700

Data Index: 683842 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.3772. Min Act: -0.1700

Data Index: 657091 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.3458. Min Act: -0.1700

Data Index: 97480 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.3302. Min Act: -0.1700

Data Index: 641688 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.3145. Min Act: -0.1700

Data Index: 167506 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2830. Min Act: -0.1700

Data Index: 637567 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2830. Min Act: -0.1700

Data Index: 970163 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2673. Min Act: -0.1700

Data Index: 757109 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2516. Min Act: -0.1700

Data Index: 251672 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2359. Min Act: -0.1700

Data Index: 1266767 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2202. Min Act: -0.1700

Data Index: 564411 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2359. Min Act: -0.1700

Data Index: 1280639 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2359. Min Act: -0.1700

Data Index: 426758 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2044. Min Act: -0.1700

Data Index: 361964 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2359. Min Act: -0.1700

Data Index: 94706 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 3.7844. Min Range: -3.7844

Max Act: 3.2202. Min Act: -0.1700

Data Index: 353914 (C4 (Web Text))

Max Activating Token Index: 98