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

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

Neuron 1924 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: 6.0467. Min Range: -6.0467

Max Act: 6.0467. Min Act: -0.1700

Data Index: 307907 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.9529. Min Act: -0.1700

Data Index: 211683 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.9842. Min Act: -0.1700

Data Index: 860811 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.9842. Min Act: -0.1700

Data Index: 810221 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8904. Min Act: -0.1700

Data Index: 353208 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.9217. Min Act: -0.1700

Data Index: 1206803 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8904. Min Act: -0.1700

Data Index: 706523 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7967. Min Act: -0.1700

Data Index: 167746 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8279. Min Act: -0.1700

Data Index: 946192 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8592. Min Act: -0.1700

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7654. Min Act: -0.1700

Data Index: 916946 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8279. Min Act: -0.1700

Data Index: 1280055 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.8279. Min Act: -0.1700

Data Index: 537478 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7654. Min Act: -0.1700

Data Index: 1248102 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7967. Min Act: -0.1700

Data Index: 965691 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7029. Min Act: -0.1700

Data Index: 258872 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7654. Min Act: -0.1700

Data Index: 598741 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7654. Min Act: -0.1700

Data Index: 297849 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.7342. Min Act: -0.1700

Data Index: 268914 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 6.0467. Min Range: -6.0467

Max Act: 5.6092. Min Act: -0.1700

Data Index: 673147 (C4 (Web Text))

Max Activating Token Index: 398