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

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

Neuron 1325 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: 3.0154. Min Range: -3.0154

Max Act: 3.0154. Min Act: -0.1700

Data Index: 205903 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.9996. Min Act: -0.1700

Data Index: 732349 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.9204. Min Act: -0.1700

Data Index: 1185241 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.9046. Min Act: -0.1700

Data Index: 1054357 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.8569. Min Act: -0.1700

Data Index: 925696 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.8411. Min Act: -0.1700

Data Index: 170619 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.8252. Min Act: -0.1700

Data Index: 302817 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.8092. Min Act: -0.1700

Data Index: 658270 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7774. Min Act: -0.1700

Data Index: 803224 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7774. Min Act: -0.1700

Data Index: 1027502 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7614. Min Act: -0.1700

Data Index: 1323551 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7455. Min Act: -0.1700

Data Index: 254841 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7295. Min Act: -0.1700

Data Index: 871126 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7295. Min Act: -0.1700

Data Index: 178333 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7295. Min Act: -0.1700

Data Index: 1140990 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6975. Min Act: -0.1700

Data Index: 9881 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.7135. Min Act: -0.1700

Data Index: 800670 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6975. Min Act: -0.1700

Data Index: 70980 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6975. Min Act: -0.1700

Data Index: 627232 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6975. Min Act: -0.1700

Data Index: 411576 (C4 (Web Text))

Max Activating Token Index: 774