Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.3473. Min Act: -0.1700

Data Index: 921398 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.3159. Min Act: -0.1699

Data Index: 38604 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.2530. Min Act: -0.1699

Data Index: 615663 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.2530. Min Act: -0.1700

Data Index: 1062597 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.2530. Min Act: -0.1700

Data Index: 931481 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.2216. Min Act: -0.1700

Data Index: 4189 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1744. Min Act: -0.1700

Data Index: 1193573 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1744. Min Act: -0.1700

Data Index: 359575 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1744. Min Act: -0.1700

Data Index: 704279 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1744. Min Act: -0.1700

Data Index: 387255 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1429. Min Act: -0.1700

Data Index: 206513 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1429. Min Act: -0.1700

Data Index: 50916 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1429. Min Act: -0.1699

Data Index: 105118 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1114. Min Act: -0.1700

Data Index: 532398 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1272. Min Act: -0.1700

Data Index: 595220 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0641. Min Act: -0.1700

Data Index: 620873 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1114. Min Act: -0.1700

Data Index: 282046 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1114. Min Act: -0.1698

Data Index: 647390 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0799. Min Act: -0.1698

Data Index: 1179232 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0799. Min Act: -0.1700

Data Index: 784165 (C4 (Web Text))

Max Activating Token Index: 352