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

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

Neuron 973 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.3651. Min Act: -0.1700

Data Index: 112173 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.3651. Min Act: -0.1700

Data Index: 801831 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.3338. Min Act: -0.1700

Data Index: 483176 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.3026. Min Act: -0.1700

Data Index: 343218 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.3338. Min Act: -0.1700

Data Index: 961747 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2713. Min Act: -0.1700

Data Index: 1064937 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2713. Min Act: -0.1700

Data Index: 991461 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2713. Min Act: -0.1700

Data Index: 1351088 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2401. Min Act: -0.1700

Data Index: 1312485 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2088. Min Act: -0.1700

Data Index: 502468 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2088. Min Act: -0.1700

Data Index: 618986 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.2088. Min Act: -0.1700

Data Index: 1004789 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 298123 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 681877 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 449988 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 400973 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 1188913 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 903688 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1463. Min Act: -0.1700

Data Index: 971728 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 5.3651. Min Range: -5.3651

Max Act: 5.1151. Min Act: -0.1700

Data Index: 415237 (C4 (Web Text))

Max Activating Token Index: 626