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

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

Neuron 1616 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1806. Min Act: -0.1700

Data Index: 115766 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1649. Min Act: -0.1700

Data Index: 734129 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1491. Min Act: -0.1700

Data Index: 1407208 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1019. Min Act: -0.1700

Data Index: 32296 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1019. Min Act: -0.1700

Data Index: 577345 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1019. Min Act: -0.1700

Data Index: 873431 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1157056 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0703. Min Act: -0.1700

Data Index: 486786 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0703. Min Act: -0.1700

Data Index: 18522 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 813954 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 417874 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 580428 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 359163 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 931439 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1275278 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 837205 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0703. Min Act: -0.1700

Data Index: 1121776 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0387. Min Act: -0.1700

Data Index: 1253387 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0387. Min Act: -0.1700

Data Index: 180326 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0545. Min Act: -0.1700

Data Index: 806308 (C4 (Web Text))

Max Activating Token Index: 869