Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.9673. Min Act: -0.1700

Data Index: 153684 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.9985. Min Act: -0.1700

Data Index: 580833 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.9360. Min Act: -0.1700

Data Index: 338923 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8891. Min Act: -0.1700

Data Index: 884925 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.9204. Min Act: -0.1700

Data Index: 488015 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8578. Min Act: -0.1700

Data Index: 944849 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8578. Min Act: -0.1700

Data Index: 1111229 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8265. Min Act: -0.1700

Data Index: 800119 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8422. Min Act: -0.1700

Data Index: 825017 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8265. Min Act: -0.1700

Data Index: 454504 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8265. Min Act: -0.1700

Data Index: 318039 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7796. Min Act: -0.1700

Data Index: 820591 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8265. Min Act: -0.1700

Data Index: 996618 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.8265. Min Act: -0.1697

Data Index: 513787 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7952. Min Act: -0.1700

Data Index: 67914 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7952. Min Act: -0.1700

Data Index: 339692 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7640. Min Act: -0.1700

Data Index: 996184 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7640. Min Act: -0.1700

Data Index: 219425 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7327. Min Act: -0.1700

Data Index: 908594 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 3.9985. Min Range: -3.9985

Max Act: 3.7640. Min Act: -0.1700

Data Index: 285752 (C4 (Web Text))

Max Activating Token Index: 988