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

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

Neuron 1445 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: 3.7599. Min Range: -3.7599

Max Act: 3.7599. Min Act: -0.1700

Data Index: 247651 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.7286. Min Act: -0.1700

Data Index: 67347 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1241261 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 885115 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 1123738 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 484454 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 91968 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 97366 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6660. Min Act: -0.1700

Data Index: 69454 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1235919 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6973. Min Act: -0.1700

Data Index: 171957 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6660. Min Act: -0.1700

Data Index: 334255 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6660. Min Act: -0.1700

Data Index: 934617 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6347. Min Act: -0.1700

Data Index: 523613 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6034. Min Act: -0.1700

Data Index: 141130 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6347. Min Act: -0.1700

Data Index: 529840 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6034. Min Act: -0.1700

Data Index: 573243 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6660. Min Act: -0.1700

Data Index: 653018 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6347. Min Act: -0.1700

Data Index: 764304 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.6347. Min Act: -0.1700

Data Index: 843790 (C4 (Web Text))

Max Activating Token Index: 347