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

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

Neuron 835 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: 11.2714. Min Range: -11.2714

Max Act: 11.2714. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.5005. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.4986. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.5157. Min Act: -0.1700

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.3616. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.1579. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 11.2714. Min Range: -11.2714

Max Act: 10.0169. Min Act: -0.1700

Data Index: 706918 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.9012. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.7472. Min Act: -0.1698

Data Index: 1439139 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.6225. Min Act: -0.1700

Data Index: 821780 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.5877. Min Act: -0.1700

Data Index: 1656685 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.5686. Min Act: -0.1700

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.5014. Min Act: -0.1700

Data Index: 871104 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.4985. Min Act: -0.1700

Data Index: 379237 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.4882. Min Act: -0.1700

Data Index: 846085 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.3383. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.3184. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.1998. Min Act: -0.1700

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.1210. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 11.2714. Min Range: -11.2714

Max Act: 9.1207. Min Act: -0.1700

Data Index: 1031872 (C4 (Web Text))

Max Activating Token Index: 991