Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1278 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0026. Min Range: -3.0026

Max Act: 3.0026. Min Act: -0.1700

Data Index: 627560 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9986. Min Act: -0.1700

Data Index: 831376 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9931. Min Act: -0.1700

Data Index: 1558373 (Python Code)

Max Activating Token Index: 301

Text #3

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9709. Min Act: -0.1700

Data Index: 1105989 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9797. Min Act: -0.1700

Data Index: 989572 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9885. Min Act: -0.1700

Data Index: 832212 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9516. Min Act: -0.1700

Data Index: 876725 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9300. Min Act: -0.1700

Data Index: 1222018 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9207. Min Act: -0.1700

Data Index: 188154 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9146. Min Act: -0.1700

Data Index: 986650 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9232. Min Act: -0.1700

Data Index: 501880 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9210. Min Act: -0.1700

Data Index: 373133 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9294. Min Act: -0.1700

Data Index: 1250476 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9083. Min Act: -0.1700

Data Index: 1402800 (Python Code)

Max Activating Token Index: 500

Text #14

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9039. Min Act: -0.1700

Data Index: 1638604 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9071. Min Act: -0.1700

Data Index: 1120999 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8868. Min Act: -0.1700

Data Index: 997632 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8746. Min Act: -0.1700

Data Index: 811865 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8848. Min Act: -0.1700

Data Index: 1451636 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8738. Min Act: -0.1700

Data Index: 811552 (C4 (Web Text))

Max Activating Token Index: 708