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

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

Neuron 1411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.6404. Min Act: -0.1700

Data Index: 338308 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.6716. Min Act: -0.1700

Data Index: 262007 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.4841. Min Act: -0.1700

Data Index: 337508 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.4841. Min Act: -0.1700

Data Index: 633422 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.5154. Min Act: -0.1700

Data Index: 1322530 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.4841. Min Act: -0.1700

Data Index: 430805 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.5154. Min Act: -0.1700

Data Index: 246955 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.4216. Min Act: -0.1700

Data Index: 1281164 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3904. Min Act: -0.1700

Data Index: 1112644 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3591. Min Act: -0.1700

Data Index: 1048865 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3591. Min Act: -0.1700

Data Index: 153770 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.2966. Min Act: -0.1700

Data Index: 579227 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3279. Min Act: -0.1700

Data Index: 1306140 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3279. Min Act: -0.1700

Data Index: 286663 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3591. Min Act: -0.1700

Data Index: 609967 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3279. Min Act: -0.1700

Data Index: 165061 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3591. Min Act: -0.1700

Data Index: 184379 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.3279. Min Act: -0.1700

Data Index: 322422 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.2966. Min Act: -0.1700

Data Index: 107949 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 5.6716. Min Range: -5.6716

Max Act: 5.2966. Min Act: -0.1700

Data Index: 749860 (C4 (Web Text))

Max Activating Token Index: 356