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

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

Neuron 1485 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1617. Min Act: -0.1700

Data Index: 100349 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1144. Min Act: -0.1700

Data Index: 158214 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0987. Min Act: -0.1700

Data Index: 1363662 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1144. Min Act: -0.1700

Data Index: 433869 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0987. Min Act: -0.1700

Data Index: 1465471 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1653038 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0514. Min Act: -0.1700

Data Index: 1493247 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0514. Min Act: -0.1700

Data Index: 1368547 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0514. Min Act: -0.1700

Data Index: 1371281 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0356. Min Act: -0.1700

Data Index: 1411430 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0198. Min Act: -0.1700

Data Index: 1432083 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0356. Min Act: -0.1700

Data Index: 1563371 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0198. Min Act: -0.1700

Data Index: 1432692 (Python Code)

Max Activating Token Index: 848

Text #13

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0198. Min Act: -0.1700

Data Index: 721975 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9881. Min Act: -0.1700

Data Index: 1458647 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0198. Min Act: -0.1700

Data Index: 1449034 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0356. Min Act: -0.1700

Data Index: 1496562 (Python Code)

Max Activating Token Index: 640

Text #17

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0040. Min Act: -0.1700

Data Index: 1592525 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0040. Min Act: -0.1700

Data Index: 1552420 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0198. Min Act: -0.1700

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 906