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

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

Neuron 1926 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.1260. Min Act: -0.1700

Data Index: 377240 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.1102. Min Act: -0.1700

Data Index: 517634 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0155. Min Act: -0.1700

Data Index: 196887 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0313. Min Act: -0.1700

Data Index: 905619 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0313. Min Act: -0.1700

Data Index: 949339 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0313. Min Act: -0.1700

Data Index: 1076510 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0313. Min Act: -0.1700

Data Index: 456192 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0155. Min Act: -0.1700

Data Index: 398511 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0155. Min Act: -0.1700

Data Index: 566757 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.1260. Min Range: -3.1260

Max Act: 3.0155. Min Act: -0.1700

Data Index: 425636 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 917260 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 641395 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 955322 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 416393 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 240874 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9997. Min Act: -0.1700

Data Index: 160557 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9839. Min Act: -0.1700

Data Index: 880498 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9839. Min Act: -0.1700

Data Index: 43728 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9839. Min Act: -0.1700

Data Index: 545606 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 3.1260. Min Range: -3.1260

Max Act: 2.9839. Min Act: -0.1700

Data Index: 926762 (C4 (Web Text))

Max Activating Token Index: 479