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

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

Neuron 1344 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7990. Min Act: -0.1700

Data Index: 1332286 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7990. Min Act: -0.1700

Data Index: 498552 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.8303. Min Act: -0.1700

Data Index: 728309 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7677. Min Act: -0.1700

Data Index: 597963 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7364. Min Act: -0.1700

Data Index: 848497 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7364. Min Act: -0.1700

Data Index: 369808 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 737482 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 65382 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 49013 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7677. Min Act: -0.1700

Data Index: 10269 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1353139 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6739. Min Act: -0.1700

Data Index: 258622 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6739. Min Act: -0.1700

Data Index: 335250 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1234188 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6739. Min Act: -0.1700

Data Index: 70704 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6739. Min Act: -0.1700

Data Index: 90302 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1091039 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6426. Min Act: -0.1700

Data Index: 401917 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1149374 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6739. Min Act: -0.1700

Data Index: 504453 (C4 (Web Text))

Max Activating Token Index: 675