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

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

Neuron 60 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: 3.6875. Min Range: -3.6875

Max Act: 3.6875. Min Act: -0.1700

Data Index: 1141809 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6768. Min Act: -0.1700

Data Index: 1095049 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6526. Min Act: -0.1700

Data Index: 845655 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5968. Min Act: -0.1700

Data Index: 346658 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6026. Min Act: -0.1700

Data Index: 909039 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1205904 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5915. Min Act: -0.1700

Data Index: 1286487 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5894. Min Act: -0.1700

Data Index: 402857 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5880. Min Act: -0.1700

Data Index: 211248 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5874. Min Act: -0.1700

Data Index: 128863 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5738. Min Act: -0.1700

Data Index: 1042956 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5734. Min Act: -0.1700

Data Index: 574554 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5665. Min Act: -0.1700

Data Index: 762972 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5710. Min Act: -0.1700

Data Index: 621916 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5786. Min Act: -0.1700

Data Index: 190465 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5699. Min Act: -0.1700

Data Index: 720028 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5860. Min Act: -0.1700

Data Index: 466039 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5492. Min Act: -0.1700

Data Index: 756527 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5570. Min Act: -0.1700

Data Index: 568102 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5661. Min Act: -0.1700

Data Index: 356536 (C4 (Web Text))

Max Activating Token Index: 46