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

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

Neuron 924 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: 3.8290. Min Range: -3.8290

Max Act: 3.8290. Min Act: -0.1700

Data Index: 1290211 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7978. Min Act: -0.1700

Data Index: 1051366 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.8290. Min Act: -0.1700

Data Index: 248086 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 1298173 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.8290. Min Act: -0.1700

Data Index: 16354 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7978. Min Act: -0.1700

Data Index: 1111441 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 979763 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 590679 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 486959 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7508. Min Act: -0.1700

Data Index: 749130 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7508. Min Act: -0.1700

Data Index: 471450 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7508. Min Act: -0.1700

Data Index: 510485 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7352. Min Act: -0.1700

Data Index: 233290 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 655828 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 138544 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 1005353 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7665. Min Act: -0.1700

Data Index: 719045 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7508. Min Act: -0.1700

Data Index: 621015 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7352. Min Act: -0.1700

Data Index: 858387 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 3.8290. Min Range: -3.8290

Max Act: 3.7352. Min Act: -0.1700

Data Index: 490923 (C4 (Web Text))

Max Activating Token Index: 754