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

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

Neuron 1426 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: 3.1875. Min Range: -3.1875

Max Act: 3.1875. Min Act: -0.1700

Data Index: 750595 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 3.1875. Min Range: -3.1875

Max Act: 3.0457. Min Act: -0.1700

Data Index: 482635 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1101475 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9666. Min Act: -0.1700

Data Index: 381201 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9508. Min Act: -0.1700

Data Index: 661690 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9666. Min Act: -0.1700

Data Index: 166306 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9508. Min Act: -0.1700

Data Index: 791905 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9666. Min Act: -0.1700

Data Index: 474878 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9033. Min Act: -0.1700

Data Index: 366015 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9191. Min Act: -0.1700

Data Index: 865631 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9033. Min Act: -0.1700

Data Index: 1051101 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9191. Min Act: -0.1700

Data Index: 1234742 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.9033. Min Act: -0.1700

Data Index: 324758 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8874. Min Act: -0.1700

Data Index: 127867 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8874. Min Act: -0.1700

Data Index: 335011 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8715. Min Act: -0.1700

Data Index: 384772 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8397. Min Act: -0.1700

Data Index: 758145 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8556. Min Act: -0.1700

Data Index: 1006297 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8397. Min Act: -0.1700

Data Index: 382453 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.1875. Min Range: -3.1875

Max Act: 2.8556. Min Act: -0.1700

Data Index: 298484 (C4 (Web Text))

Max Activating Token Index: 17