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

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

Neuron 412 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: 5.7186. Min Range: -5.7186

Max Act: 5.7186. Min Act: -0.1700

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.6873. Min Act: -0.1700

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.6248. Min Act: -0.1700

Data Index: 247075 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.5936. Min Act: -0.1700

Data Index: 1010782 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3748. Min Act: -0.1700

Data Index: 1574002 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3748. Min Act: -0.1700

Data Index: 466500 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3123. Min Act: -0.1700

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3436. Min Act: -0.1700

Data Index: 163737 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3123. Min Act: -0.1700

Data Index: 1516669 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2811. Min Act: -0.1700

Data Index: 1597215 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2811. Min Act: -0.1700

Data Index: 129559 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.3748. Min Act: -0.1700

Data Index: 595538 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2811. Min Act: -0.1700

Data Index: 400223 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2498. Min Act: -0.1700

Data Index: 1495713 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2186. Min Act: -0.1700

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2498. Min Act: -0.1700

Data Index: 1418064 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.2186. Min Act: -0.1700

Data Index: 1369532 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.1561. Min Act: -0.1700

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.1561. Min Act: -0.1700

Data Index: 1397827 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 5.7186. Min Range: -5.7186

Max Act: 5.1873. Min Act: -0.1700

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 163