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

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

Neuron 445 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: 3.1958. Min Range: -3.1958

Max Act: 3.1958. Min Act: -0.1700

Data Index: 595043 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1643. Min Act: -0.1700

Data Index: 194221 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1801. Min Act: -0.1700

Data Index: 1009398 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1643. Min Act: -0.1700

Data Index: 209748 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1328. Min Act: -0.1700

Data Index: 1260185 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1171. Min Act: -0.1700

Data Index: 50288 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1013. Min Act: -0.1700

Data Index: 408044 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1017595 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1234340 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.1013. Min Act: -0.1700

Data Index: 926034 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0855. Min Act: -0.1700

Data Index: 439730 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0698. Min Act: -0.1700

Data Index: 81351 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0855. Min Act: -0.1700

Data Index: 1073167 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0382. Min Act: -0.1700

Data Index: 866675 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0540. Min Act: -0.1700

Data Index: 1126844 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0540. Min Act: -0.1700

Data Index: 632547 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0540. Min Act: -0.1700

Data Index: 1014009 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0540. Min Act: -0.1700

Data Index: 1195413 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0540. Min Act: -0.1700

Data Index: 314429 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 3.1958. Min Range: -3.1958

Max Act: 3.0698. Min Act: -0.1700

Data Index: 1089766 (C4 (Web Text))

Max Activating Token Index: 573