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

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

Neuron 895 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.7477. Min Act: -0.1700

Data Index: 546226 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.7634. Min Act: -0.1700

Data Index: 223060 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.7164. Min Act: -0.1700

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.7164. Min Act: -0.1700

Data Index: 352473 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6225. Min Act: -0.1700

Data Index: 419470 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6538. Min Act: -0.1700

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6069. Min Act: -0.1700

Data Index: 815734 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5912. Min Act: -0.1700

Data Index: 463551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5912. Min Act: -0.1700

Data Index: 392547 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5912. Min Act: -0.1700

Data Index: 278196 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5599. Min Act: -0.1700

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6225. Min Act: -0.1700

Data Index: 1422316 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5442. Min Act: -0.1698

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5755. Min Act: -0.1700

Data Index: 1264010 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.4972. Min Act: -0.1700

Data Index: 1426606 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5442. Min Act: -0.1700

Data Index: 1201193 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5129. Min Act: -0.1700

Data Index: 882166 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.4972. Min Act: -0.1700

Data Index: 616914 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.4972. Min Act: -0.1700

Data Index: 515086 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5442. Min Act: -0.1700

Data Index: 11983 (C4 (Web Text))

Max Activating Token Index: 1023