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

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

Neuron 62 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: 3.6298. Min Range: -3.6298

Max Act: 3.6298. Min Act: -0.1700

Data Index: 791801 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.5672. Min Act: -0.1700

Data Index: 457920 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.5672. Min Act: -0.1700

Data Index: 435550 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.5045. Min Act: -0.1700

Data Index: 205228 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4732. Min Act: -0.1700

Data Index: 78066 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4418. Min Act: -0.1700

Data Index: 506868 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4418. Min Act: -0.1700

Data Index: 129754 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4105. Min Act: -0.1700

Data Index: 1272799 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3791. Min Act: -0.1700

Data Index: 159017 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3477. Min Act: -0.1700

Data Index: 823711 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3477. Min Act: -0.1700

Data Index: 91376 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3791. Min Act: -0.1700

Data Index: 369705 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1181732 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3791. Min Act: -0.1700

Data Index: 65132 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3477. Min Act: -0.1700

Data Index: 28916 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4105. Min Act: -0.1700

Data Index: 90795 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3477. Min Act: -0.1700

Data Index: 326196 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.4105. Min Act: -0.1700

Data Index: 1153958 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3477. Min Act: -0.1700

Data Index: 10483 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.6298. Min Range: -3.6298

Max Act: 3.3791. Min Act: -0.1700

Data Index: 792004 (C4 (Web Text))

Max Activating Token Index: 365