Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 592 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.7035. Min Act: -0.1700

Data Index: 509198 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.5293. Min Act: -0.1700

Data Index: 96402 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.5126. Min Act: -0.1700

Data Index: 1294785 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4614. Min Act: -0.1700

Data Index: 428440 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1060389 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4791. Min Act: -0.1700

Data Index: 345963 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4786. Min Act: -0.1700

Data Index: 1224010 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4476. Min Act: -0.1700

Data Index: 835762 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4327. Min Act: -0.1700

Data Index: 331471 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4159. Min Act: -0.1700

Data Index: 682885 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4163. Min Act: -0.1700

Data Index: 358602 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4026. Min Act: -0.1700

Data Index: 770926 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3900. Min Act: -0.1700

Data Index: 151434 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.4040. Min Act: -0.1700

Data Index: 36766 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3811. Min Act: -0.1700

Data Index: 997862 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3824. Min Act: -0.1700

Data Index: 991535 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3864. Min Act: -0.1700

Data Index: 800153 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3873. Min Act: -0.1700

Data Index: 738689 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3881. Min Act: -0.1700

Data Index: 733501 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 3.7035. Min Range: -3.7035

Max Act: 3.3941. Min Act: -0.1700

Data Index: 1089562 (C4 (Web Text))

Max Activating Token Index: 548