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

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

Neuron 1745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.5266. Min Act: -0.1700

Data Index: 716020 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.5422. Min Act: -0.1700

Data Index: 653471 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4641. Min Act: -0.1700

Data Index: 1029698 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.5422. Min Act: -0.1700

Data Index: 653286 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4016. Min Act: -0.1700

Data Index: 364552 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4172. Min Act: -0.1700

Data Index: 197028 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4016. Min Act: -0.1700

Data Index: 221943 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4016. Min Act: -0.1700

Data Index: 171104 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.4328. Min Act: -0.1700

Data Index: 560519 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3703. Min Act: -0.1700

Data Index: 271402 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3547. Min Act: -0.1700

Data Index: 60081 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3547. Min Act: -0.1700

Data Index: 579108 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3234. Min Act: -0.1700

Data Index: 1259857 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3859. Min Act: -0.1700

Data Index: 187028 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3859. Min Act: -0.1700

Data Index: 880130 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3703. Min Act: -0.1700

Data Index: 1131458 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3391. Min Act: -0.1700

Data Index: 61233 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3078. Min Act: -0.1700

Data Index: 362318 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.2766. Min Act: -0.1700

Data Index: 794514 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.3391. Min Act: -0.1700

Data Index: 617308 (C4 (Web Text))

Max Activating Token Index: 791