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

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

Neuron 470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.5403. Min Act: -0.1700

Data Index: 313257 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.3841. Min Act: -0.1700

Data Index: 334034 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.3528. Min Act: -0.1700

Data Index: 730108 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.3216. Min Act: -0.1700

Data Index: 1136255 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.3216. Min Act: -0.1700

Data Index: 977359 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.2903. Min Act: -0.1700

Data Index: 1020221 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.1966. Min Act: -0.1700

Data Index: 995850 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.1966. Min Act: -0.1700

Data Index: 1214310 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.1653. Min Act: -0.1700

Data Index: 982254 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.1341. Min Act: -0.1700

Data Index: 1260360 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1277851 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.1028. Min Act: -0.1700

Data Index: 883490 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0403. Min Act: -0.1700

Data Index: 1262000 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0716. Min Act: -0.1700

Data Index: 871093 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1172353 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0716. Min Act: -0.1700

Data Index: 900052 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0403. Min Act: -0.1700

Data Index: 781209 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0091. Min Act: -0.1700

Data Index: 746099 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0403. Min Act: -0.1700

Data Index: 210235 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 5.5403. Min Range: -5.5403

Max Act: 5.0716. Min Act: -0.1700

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 33