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

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

Neuron 1418 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9946. Min Act: -0.1700

Data Index: 3217 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8696. Min Act: -0.1700

Data Index: 298087 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9008. Min Act: -0.1700

Data Index: 1111109 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9008. Min Act: -0.1700

Data Index: 1153012 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8696. Min Act: -0.1700

Data Index: 118080 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1142208 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8696. Min Act: -0.1700

Data Index: 612909 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8383. Min Act: -0.1700

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8070. Min Act: -0.1700

Data Index: 387900 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8070. Min Act: -0.1700

Data Index: 635747 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8383. Min Act: -0.1700

Data Index: 435532 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8070. Min Act: -0.1700

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8070. Min Act: -0.1700

Data Index: 591836 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8383. Min Act: -0.1700

Data Index: 8812 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7757. Min Act: -0.1700

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8383. Min Act: -0.1700

Data Index: 339541 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7757. Min Act: -0.1700

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7757. Min Act: -0.1700

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7757. Min Act: -0.1700

Data Index: 297734 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7757. Min Act: -0.1700

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 687