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

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

Neuron 1600 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: 3.5437. Min Range: -3.5437

Max Act: 3.5437. Min Act: -0.1700

Data Index: 203371 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.5365. Min Act: -0.1700

Data Index: 208761 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.5305. Min Act: -0.1700

Data Index: 312182 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.5153. Min Act: -0.1700

Data Index: 351678 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.5024. Min Act: -0.1700

Data Index: 725587 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.5176. Min Act: -0.1700

Data Index: 943320 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4919. Min Act: -0.1700

Data Index: 1134112 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4661. Min Act: -0.1700

Data Index: 917033 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4537. Min Act: -0.1700

Data Index: 780499 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4463. Min Act: -0.1700

Data Index: 614772 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4537. Min Act: -0.1700

Data Index: 1265154 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4357. Min Act: -0.1700

Data Index: 578126 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4189. Min Act: -0.1700

Data Index: 188671 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4574. Min Act: -0.1700

Data Index: 1337405 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4494. Min Act: -0.1700

Data Index: 923523 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4309. Min Act: -0.1700

Data Index: 641599 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.4110. Min Act: -0.1700

Data Index: 263075 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.3798. Min Act: -0.1700

Data Index: 421436 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.3875. Min Act: -0.1700

Data Index: 1016979 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.5437. Min Range: -3.5437

Max Act: 3.3710. Min Act: -0.1700

Data Index: 364786 (C4 (Web Text))

Max Activating Token Index: 1001