Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1055 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.5390. Min Act: -0.1700

Data Index: 439425 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4763. Min Act: -0.1700

Data Index: 1306275 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.5076. Min Act: -0.1700

Data Index: 782379 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.5390. Min Act: -0.1700

Data Index: 497051 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4763. Min Act: -0.1700

Data Index: 704490 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.5076. Min Act: -0.1700

Data Index: 659234 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4449. Min Act: -0.1700

Data Index: 502938 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 402443 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 159789 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 762048 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4449. Min Act: -0.1700

Data Index: 454289 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 1044775 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4763. Min Act: -0.1700

Data Index: 118482 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 223405 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.3822. Min Act: -0.1700

Data Index: 99355 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.3822. Min Act: -0.1700

Data Index: 109386 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4449. Min Act: -0.1700

Data Index: 456609 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.3508. Min Act: -0.1700

Data Index: 660294 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4449. Min Act: -0.1700

Data Index: 581660 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 3.5390. Min Range: -3.5390

Max Act: 3.4136. Min Act: -0.1700

Data Index: 681135 (C4 (Web Text))

Max Activating Token Index: 129