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

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

Neuron 318 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: 3.1805. Min Range: -3.1805

Max Act: 3.1760. Min Act: -0.1700

Data Index: 464147 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1032851 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1199004 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1482. Min Act: -0.1700

Data Index: 1160533 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1396. Min Act: -0.1700

Data Index: 1316995 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1601. Min Act: -0.1700

Data Index: 381280 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1518. Min Act: -0.1700

Data Index: 195826 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1226. Min Act: -0.1700

Data Index: 1234103 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1104. Min Act: -0.1700

Data Index: 180420 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0750. Min Act: -0.1700

Data Index: 605063 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0891. Min Act: -0.1700

Data Index: 433478 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.1354. Min Act: -0.1700

Data Index: 701340 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0806. Min Act: -0.1700

Data Index: 798051 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0800. Min Act: -0.1700

Data Index: 944305 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0752. Min Act: -0.1700

Data Index: 658263 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0769. Min Act: -0.1700

Data Index: 410277 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0648. Min Act: -0.1700

Data Index: 488808 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0476. Min Act: -0.1700

Data Index: 1586470 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0274. Min Act: -0.1700

Data Index: 668392 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.1805. Min Range: -3.1805

Max Act: 3.0236. Min Act: -0.1700

Data Index: 1134314 (C4 (Web Text))

Max Activating Token Index: 246