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

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

Neuron 1989 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: 3.9539. Min Range: -3.9539

Max Act: 3.9539. Min Act: -0.1700

Data Index: 842734 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.8451. Min Act: -0.1700

Data Index: 142451 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7979. Min Act: -0.1700

Data Index: 28521 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7693. Min Act: -0.1700

Data Index: 674880 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7536. Min Act: -0.1700

Data Index: 52329 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7219. Min Act: -0.1700

Data Index: 134940 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7622. Min Act: -0.1700

Data Index: 858806 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1274354 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7593. Min Act: -0.1700

Data Index: 906772 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7162. Min Act: -0.1700

Data Index: 420248 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7217. Min Act: -0.1700

Data Index: 29448 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7503. Min Act: -0.1700

Data Index: 1199060 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1339927 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.7087. Min Act: -0.1700

Data Index: 342368 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6687. Min Act: -0.1700

Data Index: 680162 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6669. Min Act: -0.1700

Data Index: 1150211 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6701. Min Act: -0.1700

Data Index: 910482 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6765. Min Act: -0.1700

Data Index: 245559 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6773. Min Act: -0.1700

Data Index: 564205 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 3.9539. Min Range: -3.9539

Max Act: 3.6840. Min Act: -0.1700

Data Index: 912571 (C4 (Web Text))

Max Activating Token Index: 127