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

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

Neuron 1847 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: 3.9143. Min Range: -3.9143

Max Act: 3.9143. Min Act: -0.1700

Data Index: 14590 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.8830. Min Act: -0.1700

Data Index: 554734 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7579. Min Act: -0.1700

Data Index: 776935 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7579. Min Act: -0.1700

Data Index: 431023 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7266. Min Act: -0.1700

Data Index: 1072369 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7266. Min Act: -0.1700

Data Index: 878401 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.7266. Min Act: -0.1700

Data Index: 262480 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6953. Min Act: -0.1700

Data Index: 363098 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6953. Min Act: -0.1700

Data Index: 643545 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6640. Min Act: -0.1700

Data Index: 668933 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6327. Min Act: -0.1700

Data Index: 722821 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6327. Min Act: -0.1700

Data Index: 722647 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1060627 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1016526 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6327. Min Act: -0.1700

Data Index: 580426 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6014. Min Act: -0.1700

Data Index: 237900 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6014. Min Act: -0.1700

Data Index: 106046 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1225058 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6327. Min Act: -0.1700

Data Index: 884347 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.9143. Min Range: -3.9143

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1244346 (C4 (Web Text))

Max Activating Token Index: 82