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

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

Neuron 174 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: 2.7823. Min Range: -2.7823

Max Act: 2.7823. Min Act: -0.1700

Data Index: 1517645 (Python Code)

Max Activating Token Index: 801

Text #1

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7468. Min Act: -0.1700

Data Index: 471696 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7346. Min Act: -0.1700

Data Index: 754908 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7288. Min Act: -0.1699

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7278. Min Act: -0.1700

Data Index: 1548736 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7175. Min Act: -0.1700

Data Index: 1607489 (Python Code)

Max Activating Token Index: 407

Text #6

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7443. Min Act: -0.1700

Data Index: 185853 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7101. Min Act: -0.1700

Data Index: 1071120 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7253. Min Act: -0.1700

Data Index: 1491890 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7114. Min Act: -0.1700

Data Index: 1618483 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.7144. Min Act: -0.1700

Data Index: 1415770 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6736. Min Act: -0.1699

Data Index: 699784 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6767. Min Act: -0.1700

Data Index: 1436795 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6870. Min Act: -0.1700

Data Index: 1375604 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6689. Min Act: -0.1700

Data Index: 498283 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6809. Min Act: -0.1700

Data Index: 409363 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6703. Min Act: -0.1700

Data Index: 137789 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6694. Min Act: -0.1700

Data Index: 240487 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6765. Min Act: -0.1700

Data Index: 1038655 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 2.7823. Min Range: -2.7823

Max Act: 2.6637. Min Act: -0.1700

Data Index: 586833 (C4 (Web Text))

Max Activating Token Index: 865