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

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

Neuron 198 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: 3.4384. Min Range: -3.4384

Max Act: 3.4384. Min Act: -0.1700

Data Index: 1118716 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3985. Min Act: -0.1700

Data Index: 1168601 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3794. Min Act: -0.1700

Data Index: 285437 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3668. Min Act: -0.1700

Data Index: 432907 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3622. Min Act: -0.1700

Data Index: 1295747 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3743. Min Act: -0.1700

Data Index: 294500 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3507. Min Act: -0.1700

Data Index: 1181654 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3374. Min Act: -0.1694

Data Index: 505510 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3418. Min Act: -0.1700

Data Index: 612589 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3187. Min Act: -0.1700

Data Index: 1275652 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1325724 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2972. Min Act: -0.1688

Data Index: 412977 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3099. Min Act: -0.1700

Data Index: 310767 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2868. Min Act: -0.1700

Data Index: 1213023 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2642. Min Act: -0.1700

Data Index: 1344881 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2849. Min Act: -0.1700

Data Index: 1007098 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2670. Min Act: -0.1700

Data Index: 709394 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2724. Min Act: -0.1700

Data Index: 705272 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2719. Min Act: -0.1700

Data Index: 246987 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2571. Min Act: -0.1700

Data Index: 421162 (C4 (Web Text))

Max Activating Token Index: 238