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

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

Neuron 411 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: 3.1894. Min Range: -3.1894

Max Act: 3.1894. Min Act: -0.1700

Data Index: 261498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.1579. Min Act: -0.1700

Data Index: 1113995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.1421. Min Act: -0.1700

Data Index: 650415 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.0791. Min Act: -0.1700

Data Index: 396033 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.0633. Min Act: -0.1700

Data Index: 943719 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1228479 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.1894. Min Range: -3.1894

Max Act: 3.0159. Min Act: -0.1700

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9685. Min Act: -0.1700

Data Index: 672728 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9843. Min Act: -0.1700

Data Index: 1299861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9368. Min Act: -0.1700

Data Index: 1074410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 1108085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9368. Min Act: -0.1700

Data Index: 909016 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 955870 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 1056706 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 181478 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 1344811 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9210. Min Act: -0.1700

Data Index: 1171362 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9210. Min Act: -0.1700

Data Index: 29850 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9527. Min Act: -0.1700

Data Index: 812394 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.1894. Min Range: -3.1894

Max Act: 2.9368. Min Act: -0.1700

Data Index: 257138 (C4 (Web Text))

Max Activating Token Index: 177