Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1690 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.3069. Min Act: -0.1700

Data Index: 881679 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2911. Min Act: -0.1700

Data Index: 959059 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2911. Min Act: -0.1700

Data Index: 527338 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2911. Min Act: -0.1700

Data Index: 831642 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1013818 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2754. Min Act: -0.1700

Data Index: 508694 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2597. Min Act: -0.1700

Data Index: 991527 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2597. Min Act: -0.1700

Data Index: 615486 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2283. Min Act: -0.1700

Data Index: 965975 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2283. Min Act: -0.1700

Data Index: 1311168 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1445927 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.2283. Min Act: -0.1700

Data Index: 238491 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1968. Min Act: -0.1700

Data Index: 958469 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1968. Min Act: -0.1700

Data Index: 667905 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1550353 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1811. Min Act: -0.1700

Data Index: 492908 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1968. Min Act: -0.1700

Data Index: 388830 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1811. Min Act: -0.1700

Data Index: 1428159 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1811. Min Act: -0.1700

Data Index: 1414641 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 3.3069. Min Range: -3.3069

Max Act: 3.1653. Min Act: -0.1700

Data Index: 1486494 (Python Code)

Max Activating Token Index: 880