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

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

Neuron 225 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: 5.1074. Min Range: -5.1074

Max Act: 5.1074. Min Act: -0.1700

Data Index: 432339 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 5.1074. Min Range: -5.1074

Max Act: 5.0762. Min Act: -0.1700

Data Index: 926464 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.9824. Min Act: -0.1700

Data Index: 1060181 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.8574. Min Act: -0.1700

Data Index: 186060 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.8262. Min Act: -0.1700

Data Index: 1259335 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.8262. Min Act: -0.1700

Data Index: 848071 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7949. Min Act: -0.1700

Data Index: 891898 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7949. Min Act: -0.1700

Data Index: 605735 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7949. Min Act: -0.1700

Data Index: 551227 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7949. Min Act: -0.1700

Data Index: 717058 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7637. Min Act: -0.1700

Data Index: 88618 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7949. Min Act: -0.1700

Data Index: 1204911 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 1189553 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 842668 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7637. Min Act: -0.1700

Data Index: 735323 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 846710 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 785934 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.6699. Min Act: -0.1700

Data Index: 691807 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 312022 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.7324. Min Act: -0.1700

Data Index: 251186 (C4 (Web Text))

Max Activating Token Index: 138