Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 37 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0851. Min Range: -5.0851

Max Act: 5.0851. Min Act: -0.1700

Data Index: 1219973 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 5.0851. Min Range: -5.0851

Max Act: 5.0226. Min Act: -0.1700

Data Index: 1074576 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.9601. Min Act: -0.1700

Data Index: 536410 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1045862 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.9913. Min Act: -0.1700

Data Index: 184048 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 5.0851. Min Range: -5.0851

Max Act: 5.0226. Min Act: -0.1700

Data Index: 556991 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.9288. Min Act: -0.1700

Data Index: 611571 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.8038. Min Act: -0.1700

Data Index: 238926 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.8038. Min Act: -0.1700

Data Index: 860427 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6788. Min Act: -0.1700

Data Index: 943246 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.8663. Min Act: -0.1700

Data Index: 50465 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6944. Min Act: -0.1700

Data Index: 935561 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.7726. Min Act: -0.1700

Data Index: 257621 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6788. Min Act: -0.1700

Data Index: 277344 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6788. Min Act: -0.1700

Data Index: 970838 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6632. Min Act: -0.1700

Data Index: 673780 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.7101. Min Act: -0.1700

Data Index: 10384 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6007. Min Act: -0.1700

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6007. Min Act: -0.1700

Data Index: 537243 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 5.0851. Min Range: -5.0851

Max Act: 4.6476. Min Act: -0.1700

Data Index: 1037611 (C4 (Web Text))

Max Activating Token Index: 269