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

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

Neuron 1022 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.5119. Min Act: -0.1700

Data Index: 1551118 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.4182. Min Act: -0.1700

Data Index: 1536113 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.3869. Min Act: -0.1700

Data Index: 1569728 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.1682. Min Act: -0.1700

Data Index: 307280 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.1369. Min Act: -0.1700

Data Index: 1523363 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.1057. Min Act: -0.1700

Data Index: 1646445 (Python Code)

Max Activating Token Index: 451

Text #6

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.1682. Min Act: -0.1700

Data Index: 1426074 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 1560634 (Python Code)

Max Activating Token Index: 705

Text #8

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0744. Min Act: -0.1700

Data Index: 1009071 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0744. Min Act: -0.1700

Data Index: 1362867 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 1408641 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 7.5119. Min Range: -7.5119

Max Act: 6.9494. Min Act: -0.1700

Data Index: 1404662 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 1418090 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.1369. Min Act: -0.1700

Data Index: 565297 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 1397088 (Python Code)

Max Activating Token Index: 275

Text #15

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 1387998 (Python Code)

Max Activating Token Index: 429

Text #16

Max Range: 7.5119. Min Range: -7.5119

Max Act: 6.9494. Min Act: -0.1700

Data Index: 1552984 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 7.5119. Min Range: -7.5119

Max Act: 6.9807. Min Act: -0.1700

Data Index: 690801 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 7.5119. Min Range: -7.5119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 24456 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 7.5119. Min Range: -7.5119

Max Act: 6.9807. Min Act: -0.1700

Data Index: 690548 (C4 (Web Text))

Max Activating Token Index: 830