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

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

Neuron 1858 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: 3.0957. Min Range: -3.0957

Max Act: 3.0957. Min Act: -0.1700

Data Index: 811532 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 3.0957. Min Range: -3.0957

Max Act: 3.0378. Min Act: -0.1700

Data Index: 87771 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 3.0957. Min Range: -3.0957

Max Act: 3.0196. Min Act: -0.1700

Data Index: 263389 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9765. Min Act: -0.1700

Data Index: 473355 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9822. Min Act: -0.1700

Data Index: 27079 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9992. Min Act: -0.1700

Data Index: 189571 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9825. Min Act: -0.1676

Data Index: 1315002 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9572. Min Act: -0.1699

Data Index: 240356 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9580. Min Act: -0.1699

Data Index: 571729 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9283. Min Act: -0.1699

Data Index: 275939 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9256. Min Act: -0.1700

Data Index: 583918 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9010. Min Act: -0.1700

Data Index: 249588 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8978. Min Act: -0.1698

Data Index: 618241 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8974. Min Act: -0.1700

Data Index: 579208 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8920. Min Act: -0.1700

Data Index: 781161 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8844. Min Act: -0.1700

Data Index: 1308181 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8909. Min Act: -0.1700

Data Index: 991636 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9019. Min Act: -0.1700

Data Index: 805334 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8500. Min Act: -0.1699

Data Index: 800768 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8623. Min Act: -0.1700

Data Index: 104016 (C4 (Web Text))

Max Activating Token Index: 765