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

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

Neuron 782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0706. Min Range: -4.0706

Max Act: 4.0706. Min Act: -0.1700

Data Index: 1084435 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 4.0706. Min Range: -4.0706

Max Act: 4.0081. Min Act: -0.1700

Data Index: 115373 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.8830. Min Act: -0.1700

Data Index: 294424 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.7579. Min Act: -0.1700

Data Index: 1146049 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.8517. Min Act: -0.1700

Data Index: 1245007 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.7735. Min Act: -0.1700

Data Index: 265049 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.7422. Min Act: -0.1700

Data Index: 159631 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.7109. Min Act: -0.1700

Data Index: 1161756 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.7109. Min Act: -0.1700

Data Index: 1127432 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6483. Min Act: -0.1700

Data Index: 629136 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6640. Min Act: -0.1700

Data Index: 714269 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6640. Min Act: -0.1700

Data Index: 958617 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6170. Min Act: -0.1700

Data Index: 775431 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6483. Min Act: -0.1700

Data Index: 393743 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1158277 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6327. Min Act: -0.1700

Data Index: 951549 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6170. Min Act: -0.1700

Data Index: 31316 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.5857. Min Act: -0.1700

Data Index: 619235 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.5701. Min Act: -0.1700

Data Index: 499733 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 4.0706. Min Range: -4.0706

Max Act: 3.6014. Min Act: -0.1700

Data Index: 245231 (C4 (Web Text))

Max Activating Token Index: 89