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

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

Neuron 1718 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: 4.5712. Min Range: -4.5712

Max Act: 4.5712. Min Act: -0.1700

Data Index: 990679 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.2352. Min Act: -0.1700

Data Index: 680794 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.2270. Min Act: -0.1700

Data Index: 431816 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1858. Min Act: -0.1700

Data Index: 854726 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1736. Min Act: -0.1700

Data Index: 1200130 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1540. Min Act: -0.1700

Data Index: 227815 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1407. Min Act: -0.1700

Data Index: 95889 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1444. Min Act: -0.1700

Data Index: 39290 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1093. Min Act: -0.1700

Data Index: 1324626 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1249. Min Act: -0.1700

Data Index: 1110280 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1213. Min Act: -0.1700

Data Index: 582925 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.1450. Min Act: -0.1700

Data Index: 774857 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0993. Min Act: -0.1700

Data Index: 36372 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0741. Min Act: -0.1700

Data Index: 732348 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0921. Min Act: -0.1700

Data Index: 566849 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0831. Min Act: -0.1700

Data Index: 531019 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0580. Min Act: -0.1700

Data Index: 1733 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0877. Min Act: -0.1700

Data Index: 771333 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0775. Min Act: -0.1700

Data Index: 58684 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 4.5712. Min Range: -4.5712

Max Act: 4.0390. Min Act: -0.1700

Data Index: 515236 (C4 (Web Text))

Max Activating Token Index: 535