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

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

Neuron 1762 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: 4.2737. Min Range: -4.2737

Max Act: 4.2737. Min Act: -0.1700

Data Index: 633858 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.2416. Min Act: -0.1700

Data Index: 480083 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.2390. Min Act: -0.1700

Data Index: 1244521 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.2036. Min Act: -0.1698

Data Index: 1103911 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.2056. Min Act: -0.1700

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1912. Min Act: -0.1700

Data Index: 682131 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1875. Min Act: -0.1691

Data Index: 994389 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1698. Min Act: -0.1700

Data Index: 525230 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1451. Min Act: -0.1700

Data Index: 1152540 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1512. Min Act: -0.1700

Data Index: 1121475 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1394. Min Act: -0.1700

Data Index: 494730 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1406. Min Act: -0.1700

Data Index: 95836 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1357. Min Act: -0.1700

Data Index: 320234 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1328. Min Act: -0.1697

Data Index: 636694 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1593. Min Act: -0.1700

Data Index: 707723 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1444. Min Act: -0.1699

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1089. Min Act: -0.1700

Data Index: 33013 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.0914. Min Act: -0.1698

Data Index: 353289 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.1086. Min Act: -0.1700

Data Index: 55847 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 4.2737. Min Range: -4.2737

Max Act: 4.0998. Min Act: -0.1699

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 610