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

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

Neuron 1374 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: 3.1768. Min Range: -3.1768

Max Act: 3.1768. Min Act: -0.1700

Data Index: 819347 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.1768. Min Range: -3.1768

Max Act: 3.1296. Min Act: -0.1700

Data Index: 235810 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 3.1768. Min Range: -3.1768

Max Act: 3.0823. Min Act: -0.1700

Data Index: 148671 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.1768. Min Range: -3.1768

Max Act: 3.0349. Min Act: -0.1700

Data Index: 41467 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.1768. Min Range: -3.1768

Max Act: 3.0191. Min Act: -0.1700

Data Index: 163449 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9875. Min Act: -0.1700

Data Index: 1639999 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9717. Min Act: -0.1700

Data Index: 812838 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9717. Min Act: -0.1700

Data Index: 207072 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9559. Min Act: -0.1700

Data Index: 731386 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9242. Min Act: -0.1700

Data Index: 844133 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9083. Min Act: -0.1700

Data Index: 337317 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.9242. Min Act: -0.1700

Data Index: 729720 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8766. Min Act: -0.1700

Data Index: 1255280 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8925. Min Act: -0.1700

Data Index: 607825 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8607. Min Act: -0.1700

Data Index: 1057809 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8766. Min Act: -0.1700

Data Index: 868936 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8448. Min Act: -0.1700

Data Index: 231642 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8766. Min Act: -0.1700

Data Index: 511523 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8766. Min Act: -0.1700

Data Index: 1306557 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 3.1768. Min Range: -3.1768

Max Act: 2.8448. Min Act: -0.1700

Data Index: 472373 (C4 (Web Text))

Max Activating Token Index: 780