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

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

Neuron 272 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: 3.6627. Min Range: -3.6627

Max Act: 3.6627. Min Act: -0.1700

Data Index: 818565 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.4629. Min Act: -0.1700

Data Index: 797243 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.4387. Min Act: -0.1700

Data Index: 758405 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1189168 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.4065. Min Act: -0.1700

Data Index: 1044389 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3844. Min Act: -0.1700

Data Index: 847557 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3675. Min Act: -0.1700

Data Index: 11981 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3604. Min Act: -0.1700

Data Index: 647174 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3863. Min Act: -0.1700

Data Index: 599482 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3677. Min Act: -0.1700

Data Index: 1026345 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3325. Min Act: -0.1700

Data Index: 316129 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3658. Min Act: -0.1700

Data Index: 641578 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3555. Min Act: -0.1700

Data Index: 650993 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3801. Min Act: -0.1700

Data Index: 618130 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1209550 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3373. Min Act: -0.1700

Data Index: 929228 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3409. Min Act: -0.1700

Data Index: 856074 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3295. Min Act: -0.1700

Data Index: 483919 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3322. Min Act: -0.1700

Data Index: 539005 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 3.6627. Min Range: -3.6627

Max Act: 3.3428. Min Act: -0.1700

Data Index: 584736 (C4 (Web Text))

Max Activating Token Index: 218