Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2703. Min Act: -0.1700

Data Index: 33357 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2703. Min Act: -0.1700

Data Index: 936253 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2390. Min Act: -0.1700

Data Index: 163510 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2703. Min Act: -0.1700

Data Index: 1341250 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2078. Min Act: -0.1700

Data Index: 1137008 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2078. Min Act: -0.1700

Data Index: 1159642 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.2078. Min Act: -0.1700

Data Index: 909114 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 1615032 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 345248 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1452. Min Act: -0.1700

Data Index: 279852 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 78781 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 287592 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 799052 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1452. Min Act: -0.1700

Data Index: 639847 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 725096 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 677527 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1765. Min Act: -0.1700

Data Index: 773594 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1452. Min Act: -0.1700

Data Index: 97435 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1452. Min Act: -0.1700

Data Index: 91709 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1452. Min Act: -0.1700

Data Index: 1033657 (C4 (Web Text))

Max Activating Token Index: 762