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

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

Neuron 1478 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0019. Min Range: -3.0019

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1273732 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 3.0019. Min Range: -3.0019

Max Act: 3.0019. Min Act: -0.1700

Data Index: 349430 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9702. Min Act: -0.1700

Data Index: 244772 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9544. Min Act: -0.1700

Data Index: 924085 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9702. Min Act: -0.1700

Data Index: 617714 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9544. Min Act: -0.1700

Data Index: 290339 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9860. Min Act: -0.1700

Data Index: 710075 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9702. Min Act: -0.1700

Data Index: 131226 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9544. Min Act: -0.1700

Data Index: 191862 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9702. Min Act: -0.1700

Data Index: 984174 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9386. Min Act: -0.1700

Data Index: 39171 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 995632 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 196770 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 138955 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 1005686 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 1032401 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9227. Min Act: -0.1700

Data Index: 654256 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9069. Min Act: -0.1700

Data Index: 866390 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.8910. Min Act: -0.1700

Data Index: 463071 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.9069. Min Act: -0.1700

Data Index: 919893 (C4 (Web Text))

Max Activating Token Index: 603