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

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

Neuron 1646 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: 3.1369. Min Range: -3.1369

Max Act: 3.1369. Min Act: -0.1700

Data Index: 1206815 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.1211. Min Act: -0.1700

Data Index: 814852 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.1211. Min Act: -0.1700

Data Index: 792403 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.1211. Min Act: -0.1700

Data Index: 692451 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.1054. Min Act: -0.1700

Data Index: 12723 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 821784 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.1054. Min Act: -0.1700

Data Index: 444149 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0580. Min Act: -0.1700

Data Index: 782210 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 538167 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0580. Min Act: -0.1700

Data Index: 789022 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0580. Min Act: -0.1700

Data Index: 486153 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0580. Min Act: -0.1700

Data Index: 48880 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 965422 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 12070 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 994446 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 1095449 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0423. Min Act: -0.1700

Data Index: 473528 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0738. Min Act: -0.1700

Data Index: 1184034 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0423. Min Act: -0.1700

Data Index: 94456 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 3.1369. Min Range: -3.1369

Max Act: 3.0580. Min Act: -0.1700

Data Index: 774950 (C4 (Web Text))

Max Activating Token Index: 179