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

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

Neuron 835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1685. Min Range: -7.1685

Max Act: 7.1685. Min Act: -0.1700

Data Index: 1391168 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.6528. Min Act: -0.1700

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.6372. Min Act: -0.1700

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.5591. Min Act: -0.1700

Data Index: 769946 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.6060. Min Act: -0.1700

Data Index: 467973 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.4966. Min Act: -0.1700

Data Index: 1614571 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.4810. Min Act: -0.1700

Data Index: 173602 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.4810. Min Act: -0.1698

Data Index: 444002 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.3403. Min Act: -0.1700

Data Index: 1016165 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.3872. Min Act: -0.1700

Data Index: 112534 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.4028. Min Act: -0.1700

Data Index: 654309 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.3716. Min Act: -0.1700

Data Index: 159570 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.4028. Min Act: -0.1700

Data Index: 975124 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.2466. Min Act: -0.1700

Data Index: 1220328 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.1372. Min Act: -0.1700

Data Index: 629107 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.2153. Min Act: -0.1700

Data Index: 223605 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.2153. Min Act: -0.1700

Data Index: 1122243 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.2310. Min Act: -0.1700

Data Index: 649746 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.0903. Min Act: -0.1700

Data Index: 473360 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 7.1685. Min Range: -7.1685

Max Act: 6.0278. Min Act: -0.1700

Data Index: 204418 (C4 (Web Text))

Max Activating Token Index: 736