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

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

Neuron 815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.7845. Min Act: -0.1700

Data Index: 626164 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.7219. Min Act: -0.1700

Data Index: 524456 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6594. Min Act: -0.1700

Data Index: 801700 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6907. Min Act: -0.1700

Data Index: 860733 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6594. Min Act: -0.1700

Data Index: 161461 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.6280. Min Act: -0.1700

Data Index: 1141950 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 322341 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 105405 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1195987 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 275860 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5341. Min Act: -0.1700

Data Index: 82579 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1049429 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5341. Min Act: -0.1700

Data Index: 5921 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5028. Min Act: -0.1700

Data Index: 553384 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 397322 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1093652 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 21465 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5967. Min Act: -0.1700

Data Index: 141403 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5028. Min Act: -0.1700

Data Index: 650687 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 3.7845. Min Range: -3.7845

Max Act: 3.5341. Min Act: -0.1700

Data Index: 512097 (C4 (Web Text))

Max Activating Token Index: 281