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

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

Neuron 217 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: 3.9734. Min Range: -3.9734

Max Act: 3.9734. Min Act: -0.1700

Data Index: 678290 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.9422. Min Act: -0.1700

Data Index: 1235667 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.9109. Min Act: -0.1700

Data Index: 826895 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 840005 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 305628 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 106146 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 1027857 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 1046133 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8483. Min Act: -0.1700

Data Index: 796952 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8483. Min Act: -0.1700

Data Index: 7146 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8796. Min Act: -0.1700

Data Index: 1252851 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8483. Min Act: -0.1700

Data Index: 321343 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7858. Min Act: -0.1700

Data Index: 766379 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7858. Min Act: -0.1700

Data Index: 88272 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8171. Min Act: -0.1700

Data Index: 568625 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.8171. Min Act: -0.1700

Data Index: 275507 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7858. Min Act: -0.1700

Data Index: 992220 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7858. Min Act: -0.1700

Data Index: 416305 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7858. Min Act: -0.1700

Data Index: 983995 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.9734. Min Range: -3.9734

Max Act: 3.7545. Min Act: -0.1700

Data Index: 870337 (C4 (Web Text))

Max Activating Token Index: 270