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

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

Neuron 1977 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: 5.6509. Min Range: -5.6509

Max Act: 5.6509. Min Act: -0.1700

Data Index: 225295 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.6176. Min Act: -0.1700

Data Index: 1144229 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.4666. Min Act: -0.1700

Data Index: 1098430 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.4376. Min Act: -0.1699

Data Index: 205962 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.4374. Min Act: -0.1700

Data Index: 861665 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3892. Min Act: -0.1700

Data Index: 705190 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3927. Min Act: -0.1700

Data Index: 335913 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3745. Min Act: -0.1700

Data Index: 707158 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3959. Min Act: -0.1700

Data Index: 861297 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3793. Min Act: -0.1700

Data Index: 736355 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3353. Min Act: -0.1700

Data Index: 1075421 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3642. Min Act: -0.1700

Data Index: 146971 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3465. Min Act: -0.1700

Data Index: 589001 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3309. Min Act: -0.1700

Data Index: 1085016 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.2878. Min Act: -0.1700

Data Index: 347799 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.3211. Min Act: -0.1700

Data Index: 684945 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.2917. Min Act: -0.1700

Data Index: 1052739 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.2959. Min Act: -0.1699

Data Index: 773140 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.2663. Min Act: -0.1700

Data Index: 1037372 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.2642. Min Act: -0.1700

Data Index: 263364 (C4 (Web Text))

Max Activating Token Index: 418