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

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

Neuron 626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.5032. Min Act: -0.1699

Data Index: 999224 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.2532. Min Act: -0.1700

Data Index: 36512 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.2376. Min Act: -0.1700

Data Index: 431572 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.2219. Min Act: -0.1700

Data Index: 1021617 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.2376. Min Act: -0.1700

Data Index: 1198913 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.2219. Min Act: -0.1700

Data Index: 939540 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.1282. Min Act: -0.1700

Data Index: 609415 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.1438. Min Act: -0.1700

Data Index: 522492 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0657. Min Act: -0.1700

Data Index: 197358 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.1594. Min Act: -0.1700

Data Index: 853048 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0813. Min Act: -0.1699

Data Index: 1286507 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0969. Min Act: -0.1699

Data Index: 231099 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0501. Min Act: -0.1700

Data Index: 114849 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0501. Min Act: -0.1700

Data Index: 66991 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0501. Min Act: -0.1700

Data Index: 220066 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 5.5032. Min Range: -5.5032

Max Act: 4.9876. Min Act: -0.1700

Data Index: 1098083 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 5.5032. Min Range: -5.5032

Max Act: 4.9876. Min Act: -0.1700

Data Index: 284733 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 5.5032. Min Range: -5.5032

Max Act: 5.0188. Min Act: -0.1700

Data Index: 157673 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 5.5032. Min Range: -5.5032

Max Act: 4.9876. Min Act: -0.1700

Data Index: 1026043 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 5.5032. Min Range: -5.5032

Max Act: 4.9563. Min Act: -0.1700

Data Index: 637424 (C4 (Web Text))

Max Activating Token Index: 386