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

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

Neuron 1818 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: 5.5786. Min Range: -5.5786

Max Act: 5.5786. Min Act: -0.1700

Data Index: 752338 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.2974. Min Act: -0.1700

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1411. Min Act: -0.1700

Data Index: 1255266 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1724. Min Act: -0.1700

Data Index: 1267974 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1099. Min Act: -0.1700

Data Index: 1324780 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1724. Min Act: -0.1700

Data Index: 365772 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1411. Min Act: -0.1700

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1099. Min Act: -0.1700

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1099. Min Act: -0.1700

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.0161. Min Act: -0.1700

Data Index: 938613 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.1411. Min Act: -0.1700

Data Index: 108057 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.9224. Min Act: -0.1700

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 5.5786. Min Range: -5.5786

Max Act: 5.0786. Min Act: -0.1700

Data Index: 606128 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.8599. Min Act: -0.1700

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.9224. Min Act: -0.1700

Data Index: 798139 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.8599. Min Act: -0.1700

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.9536. Min Act: -0.1700

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.8286. Min Act: -0.1700

Data Index: 740362 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.7974. Min Act: -0.1700

Data Index: 817899 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 5.5786. Min Range: -5.5786

Max Act: 4.8599. Min Act: -0.1700

Data Index: 418730 (C4 (Web Text))

Max Activating Token Index: 170