Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1124 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9376. Min Act: -0.1677

Data Index: 776638 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6004. Min Act: -0.1699

Data Index: 855248 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.5290. Min Act: -0.1700

Data Index: 1214744 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.5234. Min Act: -0.1688

Data Index: 190852 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4991. Min Act: -0.1677

Data Index: 861043 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4952. Min Act: -0.1700

Data Index: 1031270 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4880. Min Act: -0.1677

Data Index: 1004210 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4729. Min Act: -0.1694

Data Index: 515977 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4766. Min Act: -0.1699

Data Index: 1206128 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4550. Min Act: -0.1677

Data Index: 891370 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4645. Min Act: -0.1677

Data Index: 1325617 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4539. Min Act: -0.1691

Data Index: 253571 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4490. Min Act: -0.1677

Data Index: 62996 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4565. Min Act: -0.1677

Data Index: 463277 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4360. Min Act: -0.1679

Data Index: 832641 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4198. Min Act: -0.1700

Data Index: 160345 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4188. Min Act: -0.1695

Data Index: 824422 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.4046. Min Act: -0.1699

Data Index: 1091383 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.3983. Min Act: -0.1686

Data Index: 815527 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.3887. Min Act: -0.1700

Data Index: 506078 (C4 (Web Text))

Max Activating Token Index: 199