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

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

Neuron 1482 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: 3.7308. Min Range: -3.7308

Max Act: 3.7308. Min Act: -0.1700

Data Index: 1241121 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.5214. Min Act: -0.1700

Data Index: 459631 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.5423. Min Act: -0.1700

Data Index: 137344 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4589. Min Act: -0.1700

Data Index: 170991 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4759. Min Act: -0.1700

Data Index: 1236096 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4556. Min Act: -0.1700

Data Index: 408557 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4304. Min Act: -0.1700

Data Index: 285427 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4556. Min Act: -0.1700

Data Index: 903454 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4233. Min Act: -0.1700

Data Index: 613551 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4364. Min Act: -0.1700

Data Index: 593599 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4029. Min Act: -0.1700

Data Index: 358177 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4131. Min Act: -0.1700

Data Index: 430726 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4138. Min Act: -0.1700

Data Index: 161141 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1073080 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4427. Min Act: -0.1700

Data Index: 334973 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1076283 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4138. Min Act: -0.1700

Data Index: 954597 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4011. Min Act: -0.1700

Data Index: 913478 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4144. Min Act: -0.1700

Data Index: 486765 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 3.7308. Min Range: -3.7308

Max Act: 3.4118. Min Act: -0.1700

Data Index: 1238486 (C4 (Web Text))

Max Activating Token Index: 579