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

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

Neuron 1809 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.2441. Min Act: -0.1700

Data Index: 136947 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.2127. Min Act: -0.1700

Data Index: 436030 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.2284. Min Act: -0.1700

Data Index: 1351056 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.2127. Min Act: -0.1700

Data Index: 914062 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.2127. Min Act: -0.1700

Data Index: 652259 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1970. Min Act: -0.1700

Data Index: 23276 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1655. Min Act: -0.1700

Data Index: 767775 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1812. Min Act: -0.1700

Data Index: 328997 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1497. Min Act: -0.1700

Data Index: 49617 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1812. Min Act: -0.1700

Data Index: 396491 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1152968 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1497. Min Act: -0.1700

Data Index: 987646 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1497. Min Act: -0.1700

Data Index: 1042191 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1497. Min Act: -0.1700

Data Index: 360882 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 205608 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1134222 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1273566 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1182. Min Act: -0.1700

Data Index: 1346970 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 51881 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.2441. Min Range: -3.2441

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1063862 (C4 (Web Text))

Max Activating Token Index: 983