Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1844 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1332. Min Range: -4.1332

Max Act: 4.1332. Min Act: -0.1700

Data Index: 875612 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 4.1332. Min Range: -4.1332

Max Act: 4.0081. Min Act: -0.1700

Data Index: 1247881 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.9769. Min Act: -0.1700

Data Index: 609659 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.9143. Min Act: -0.1700

Data Index: 1222175 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.9143. Min Act: -0.1700

Data Index: 979033 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.8362. Min Act: -0.1700

Data Index: 1040771 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.9143. Min Act: -0.1700

Data Index: 1047492 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7267. Min Act: -0.1700

Data Index: 957983 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7736. Min Act: -0.1700

Data Index: 864819 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7580. Min Act: -0.1700

Data Index: 1100267 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7892. Min Act: -0.1700

Data Index: 743146 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7423. Min Act: -0.1700

Data Index: 404739 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7267. Min Act: -0.1700

Data Index: 1093333 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7267. Min Act: -0.1700

Data Index: 707759 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7267. Min Act: -0.1700

Data Index: 297405 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7423. Min Act: -0.1700

Data Index: 570282 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7736. Min Act: -0.1700

Data Index: 1023129 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.6954. Min Act: -0.1700

Data Index: 336263 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7423. Min Act: -0.1700

Data Index: 1310116 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 4.1332. Min Range: -4.1332

Max Act: 3.7267. Min Act: -0.1700

Data Index: 729919 (C4 (Web Text))

Max Activating Token Index: 60