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

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

Neuron 1885 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0000. Min Range: -3.0000

Max Act: 3.0000. Min Act: -0.1700

Data Index: 1148366 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 3.0000. Min Range: -3.0000

Max Act: 3.0000. Min Act: -0.1700

Data Index: 46688 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.0000. Min Range: -3.0000

Max Act: 3.0000. Min Act: -0.1700

Data Index: 1285396 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9209. Min Act: -0.1700

Data Index: 700181 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9525. Min Act: -0.1700

Data Index: 29504 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.8891. Min Act: -0.1700

Data Index: 784488 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9525. Min Act: -0.1700

Data Index: 756146 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9209. Min Act: -0.1700

Data Index: 1107504 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9209. Min Act: -0.1700

Data Index: 227290 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9050. Min Act: -0.1700

Data Index: 578447 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9525. Min Act: -0.1700

Data Index: 86145 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9684. Min Act: -0.1700

Data Index: 383710 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9367. Min Act: -0.1700

Data Index: 31435 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9050. Min Act: -0.1700

Data Index: 90442 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9050. Min Act: -0.1700

Data Index: 741063 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9367. Min Act: -0.1700

Data Index: 1253022 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9525. Min Act: -0.1700

Data Index: 639130 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9209. Min Act: -0.1700

Data Index: 644068 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.8891. Min Act: -0.1700

Data Index: 343858 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 3.0000. Min Range: -3.0000

Max Act: 2.9050. Min Act: -0.1700

Data Index: 1100955 (C4 (Web Text))

Max Activating Token Index: 507