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

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

Neuron 337 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: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 600568 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4158. Min Act: -0.1699

Data Index: 537553 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3957. Min Act: -0.1700

Data Index: 777673 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3764. Min Act: -0.1699

Data Index: 970450 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3697. Min Act: -0.1700

Data Index: 688959 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3237. Min Act: -0.1700

Data Index: 920849 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2857. Min Act: -0.1700

Data Index: 1154812 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2852. Min Act: -0.1683

Data Index: 643443 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2885. Min Act: -0.1700

Data Index: 288493 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2832. Min Act: -0.1700

Data Index: 343870 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2581. Min Act: -0.1700

Data Index: 681864 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2309. Min Act: -0.1700

Data Index: 1252047 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2301. Min Act: -0.1695

Data Index: 382261 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2347. Min Act: -0.1700

Data Index: 817274 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2272. Min Act: -0.1539

Data Index: 793466 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2311. Min Act: -0.1699

Data Index: 1097410 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2044. Min Act: -0.1700

Data Index: 474018 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2026. Min Act: -0.1698

Data Index: 10679 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2067. Min Act: -0.1700

Data Index: 531620 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.2018. Min Act: -0.1700

Data Index: 194337 (C4 (Web Text))

Max Activating Token Index: 597