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

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

Neuron 374 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: 3.0877. Min Range: -3.0877

Max Act: 3.0877. Min Act: -0.1700

Data Index: 290286 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0698. Min Act: -0.1696

Data Index: 1137107 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0488. Min Act: -0.1700

Data Index: 1533285 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0332. Min Act: -0.1700

Data Index: 23224 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9972. Min Act: -0.1700

Data Index: 552827 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0112. Min Act: -0.1700

Data Index: 1609460 (Python Code)

Max Activating Token Index: 250

Text #6

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9935. Min Act: -0.1700

Data Index: 1032243 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0124. Min Act: -0.1700

Data Index: 1040308 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 3.0877. Min Range: -3.0877

Max Act: 3.0167. Min Act: -0.1700

Data Index: 170505 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9909. Min Act: -0.1700

Data Index: 97839 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9890. Min Act: -0.1700

Data Index: 352223 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9929. Min Act: -0.1700

Data Index: 399534 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1609500 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9729. Min Act: -0.1700

Data Index: 1403862 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9608. Min Act: -0.1700

Data Index: 1023872 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9592. Min Act: -0.1700

Data Index: 1114283 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9587. Min Act: -0.1700

Data Index: 347360 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9626. Min Act: -0.1700

Data Index: 1277011 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9452. Min Act: -0.1700

Data Index: 1161789 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.0877. Min Range: -3.0877

Max Act: 2.9507. Min Act: -0.1700

Data Index: 1580742 (Python Code)

Max Activating Token Index: 315