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

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

Neuron 1758 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.4911. Min Act: -0.1700

Data Index: 515616 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.2098. Min Act: -0.1700

Data Index: 972351 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.1161. Min Act: -0.1700

Data Index: 1206867 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.1161. Min Act: -0.1700

Data Index: 1250982 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.0536. Min Act: -0.1700

Data Index: 418896 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.0848. Min Act: -0.1700

Data Index: 534819 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 7.4911. Min Range: -7.4911

Max Act: 7.0848. Min Act: -0.1700

Data Index: 390746 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9911. Min Act: -0.1700

Data Index: 528222 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9911. Min Act: -0.1700

Data Index: 731786 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9911. Min Act: -0.1700

Data Index: 1117813 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9286. Min Act: -0.1700

Data Index: 854950 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8973. Min Act: -0.1700

Data Index: 626596 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9598. Min Act: -0.1700

Data Index: 1320033 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.9286. Min Act: -0.1700

Data Index: 139393 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8348. Min Act: -0.1700

Data Index: 459657 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8973. Min Act: -0.1700

Data Index: 164243 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8661. Min Act: -0.1700

Data Index: 246933 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8661. Min Act: -0.1700

Data Index: 1228987 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8973. Min Act: -0.1700

Data Index: 334667 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 7.4911. Min Range: -7.4911

Max Act: 6.8348. Min Act: -0.1700

Data Index: 1300294 (C4 (Web Text))

Max Activating Token Index: 464