Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 953 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.9146. Min Act: -0.1700

Data Index: 317188 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8834. Min Act: -0.1700

Data Index: 404102 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8834. Min Act: -0.1700

Data Index: 665200 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8521. Min Act: -0.1700

Data Index: 501736 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8521. Min Act: -0.1700

Data Index: 756540 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8834. Min Act: -0.1700

Data Index: 1350734 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7895. Min Act: -0.1700

Data Index: 266639 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8208. Min Act: -0.1700

Data Index: 873007 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8208. Min Act: -0.1700

Data Index: 433002 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7895. Min Act: -0.1700

Data Index: 1294128 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 283093 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.8208. Min Act: -0.1700

Data Index: 984430 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 155927 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.6957. Min Act: -0.1700

Data Index: 390076 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7895. Min Act: -0.1700

Data Index: 25592 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 683892 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1102061 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 553073 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 618112 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 3.9146. Min Range: -3.9146

Max Act: 3.7583. Min Act: -0.1700

Data Index: 188737 (C4 (Web Text))

Max Activating Token Index: 115