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

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

Neuron 1085 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: 3.7807. Min Range: -3.7807

Max Act: 3.7807. Min Act: -0.1700

Data Index: 1624566 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.7795. Min Act: -0.1700

Data Index: 1381532 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1413848 (Python Code)

Max Activating Token Index: 384

Text #3

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1473155 (Python Code)

Max Activating Token Index: 755

Text #4

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.6761. Min Act: -0.1700

Data Index: 1398086 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5980. Min Act: -0.1700

Data Index: 1070580 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5970. Min Act: -0.1700

Data Index: 537104 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.6009. Min Act: -0.1700

Data Index: 873248 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1270315 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5765. Min Act: -0.1700

Data Index: 1054456 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5765. Min Act: -0.1700

Data Index: 324754 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5683. Min Act: -0.1700

Data Index: 1570440 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5640. Min Act: -0.1700

Data Index: 919611 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5624. Min Act: -0.1700

Data Index: 732201 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1558745 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5230. Min Act: -0.1700

Data Index: 1260173 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5135. Min Act: -0.1700

Data Index: 911624 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5306. Min Act: -0.1700

Data Index: 960430 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5286. Min Act: -0.1700

Data Index: 1164133 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5033. Min Act: -0.1700

Data Index: 892300 (C4 (Web Text))

Max Activating Token Index: 824