Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1069 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.7334. Min Act: -0.1700

Data Index: 761484 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.6709. Min Act: -0.1700

Data Index: 283871 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5772. Min Act: -0.1700

Data Index: 75511 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.6397. Min Act: -0.1700

Data Index: 177141 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5772. Min Act: -0.1700

Data Index: 461746 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5459. Min Act: -0.1700

Data Index: 822396 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5459. Min Act: -0.1700

Data Index: 724408 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5772. Min Act: -0.1700

Data Index: 899598 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5459. Min Act: -0.1700

Data Index: 715657 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 1028834 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 1303077 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5459. Min Act: -0.1700

Data Index: 180856 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.4834. Min Act: -0.1700

Data Index: 210629 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 1123464 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 294161 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.4834. Min Act: -0.1700

Data Index: 187900 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.4522. Min Act: -0.1700

Data Index: 661524 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 570575 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.5147. Min Act: -0.1700

Data Index: 487308 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 5.7334. Min Range: -5.7334

Max Act: 5.4522. Min Act: -0.1700

Data Index: 1140224 (C4 (Web Text))

Max Activating Token Index: 557