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

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

Neuron 955 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: 3.7443. Min Range: -3.7443

Max Act: 3.7443. Min Act: -0.1700

Data Index: 1315708 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.7060. Min Act: -0.1700

Data Index: 418078 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.6295. Min Act: -0.1700

Data Index: 3241 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.6102. Min Act: -0.1700

Data Index: 129558 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4889. Min Act: -0.1700

Data Index: 680772 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.5259. Min Act: -0.1700

Data Index: 275522 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4950. Min Act: -0.1700

Data Index: 127345 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4882. Min Act: -0.1700

Data Index: 352050 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4587. Min Act: -0.1700

Data Index: 1187322 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4690. Min Act: -0.1700

Data Index: 985934 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4498. Min Act: -0.1700

Data Index: 1051586 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3863. Min Act: -0.1700

Data Index: 969125 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1064820 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3826. Min Act: -0.1700

Data Index: 692472 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3951. Min Act: -0.1700

Data Index: 525322 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.4018. Min Act: -0.1700

Data Index: 705883 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3778. Min Act: -0.1700

Data Index: 952112 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3526. Min Act: -0.1700

Data Index: 640814 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3262. Min Act: -0.1700

Data Index: 728861 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 3.7443. Min Range: -3.7443

Max Act: 3.3602. Min Act: -0.1700

Data Index: 859919 (C4 (Web Text))

Max Activating Token Index: 755