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

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

Neuron 1495 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: 12.6862. Min Range: -12.6862

Max Act: 12.6862. Min Act: -0.1700

Data Index: 486756 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.3745. Min Act: -0.1700

Data Index: 599876 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.2624. Min Act: -0.1699

Data Index: 860372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.3182. Min Act: -0.1700

Data Index: 681805 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.1580. Min Act: -0.1700

Data Index: 643199 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.0274. Min Act: -0.1700

Data Index: 260007 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.2007. Min Act: -0.1700

Data Index: 584832 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.1272. Min Act: -0.1700

Data Index: 456791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.1692. Min Act: -0.1699

Data Index: 455961 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.1477. Min Act: -0.1700

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.0608. Min Act: -0.1699

Data Index: 1192341 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.2045. Min Act: -0.1700

Data Index: 770264 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 12.6862. Min Range: -12.6862

Max Act: 12.0907. Min Act: -0.1700

Data Index: 1148888 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.8079. Min Act: -0.1699

Data Index: 585663 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.9546. Min Act: -0.1698

Data Index: 906850 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.8153. Min Act: -0.1699

Data Index: 921 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.8322. Min Act: -0.1700

Data Index: 808332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.9686. Min Act: -0.1700

Data Index: 83587 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.7600. Min Act: -0.1699

Data Index: 464927 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 12.6862. Min Range: -12.6862

Max Act: 11.9075. Min Act: -0.1696

Data Index: 217648 (C4 (Web Text))

Max Activating Token Index: 1023