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

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

Neuron 162 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: 4.2050. Min Range: -4.2050

Max Act: 4.2050. Min Act: -0.1700

Data Index: 536398 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.1772. Min Act: -0.1700

Data Index: 1061600 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.1326. Min Act: -0.1700

Data Index: 1369823 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.1151. Min Act: -0.1700

Data Index: 320428 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0970. Min Act: -0.1696

Data Index: 548553 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0927. Min Act: -0.1697

Data Index: 1341373 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0784. Min Act: -0.1608

Data Index: 1262001 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0482. Min Act: -0.1700

Data Index: 473497 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0322. Min Act: -0.1700

Data Index: 314018 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0472. Min Act: -0.1700

Data Index: 1043566 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9823. Min Act: -0.1700

Data Index: 429057 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1212225 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9666. Min Act: -0.1700

Data Index: 1598630 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9039. Min Act: -0.1700

Data Index: 1332225 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9436. Min Act: -0.1700

Data Index: 459729 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9338. Min Act: -0.1698

Data Index: 709296 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.8891. Min Act: -0.1700

Data Index: 314773 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9197. Min Act: -0.1700

Data Index: 666699 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9083. Min Act: -0.1700

Data Index: 684558 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9074. Min Act: -0.1700

Data Index: 1568748 (Python Code)

Max Activating Token Index: 623