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

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

Neuron 770 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0022. Min Range: -3.0022

Max Act: 3.0022. Min Act: -0.1700

Data Index: 615067 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.0022. Min Range: -3.0022

Max Act: 3.0022. Min Act: -0.1700

Data Index: 1038643 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9706. Min Act: -0.1700

Data Index: 470230 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9864. Min Act: -0.1700

Data Index: 590191 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9548. Min Act: -0.1700

Data Index: 1272624 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9706. Min Act: -0.1700

Data Index: 1352180 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9548. Min Act: -0.1700

Data Index: 1074182 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9231. Min Act: -0.1700

Data Index: 1227905 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9389. Min Act: -0.1700

Data Index: 1150593 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9389. Min Act: -0.1700

Data Index: 961662 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9389. Min Act: -0.1700

Data Index: 158824 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9072. Min Act: -0.1700

Data Index: 209158 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9389. Min Act: -0.1700

Data Index: 849508 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9231. Min Act: -0.1700

Data Index: 535933 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9231. Min Act: -0.1700

Data Index: 1038596 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9231. Min Act: -0.1700

Data Index: 344379 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9072. Min Act: -0.1700

Data Index: 584895 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9072. Min Act: -0.1700

Data Index: 1142360 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9072. Min Act: -0.1700

Data Index: 347803 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9231. Min Act: -0.1700

Data Index: 248057 (C4 (Web Text))

Max Activating Token Index: 726