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

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

Neuron 303 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: 3.3967. Min Range: -3.3967

Max Act: 3.3967. Min Act: -0.1700

Data Index: 975710 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3653. Min Act: -0.1700

Data Index: 841171 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 587428 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3653. Min Act: -0.1700

Data Index: 1075608 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3339. Min Act: -0.1700

Data Index: 671544 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 277691 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2868. Min Act: -0.1700

Data Index: 999373 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2868. Min Act: -0.1700

Data Index: 1056937 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 1091227 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 198214 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 1018117 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.3025. Min Act: -0.1700

Data Index: 788195 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2554. Min Act: -0.1700

Data Index: 235312 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1045957 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2711. Min Act: -0.1700

Data Index: 673452 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2711. Min Act: -0.1700

Data Index: 42267 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2711. Min Act: -0.1700

Data Index: 760602 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2711. Min Act: -0.1700

Data Index: 1213397 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1120304 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.3967. Min Range: -3.3967

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1120519 (C4 (Web Text))

Max Activating Token Index: 802