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

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

Neuron 89 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: 3.6522. Min Range: -3.6522

Max Act: 3.6522. Min Act: -0.1700

Data Index: 27044 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5826. Min Act: -0.1700

Data Index: 331526 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5698. Min Act: -0.1699

Data Index: 1355595 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5421. Min Act: -0.1693

Data Index: 846104 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5528. Min Act: -0.1700

Data Index: 1305078 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5169. Min Act: -0.1700

Data Index: 1276945 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5133. Min Act: -0.1700

Data Index: 1083850 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5297. Min Act: -0.1700

Data Index: 1289406 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4738. Min Act: -0.1700

Data Index: 111229 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4736. Min Act: -0.1575

Data Index: 114273 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4781. Min Act: -0.1700

Data Index: 1238236 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1347516 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1065104 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4385. Min Act: -0.1700

Data Index: 413826 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4577. Min Act: -0.1700

Data Index: 713318 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4247. Min Act: -0.1699

Data Index: 263792 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4245. Min Act: -0.1368

Data Index: 1265502 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4124. Min Act: -0.1700

Data Index: 346715 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3909. Min Act: -0.1700

Data Index: 1133795 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3852. Min Act: -0.1699

Data Index: 586715 (C4 (Web Text))

Max Activating Token Index: 100