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

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

Neuron 1024 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: 4.9036. Min Range: -4.9036

Max Act: 4.9036. Min Act: -0.1700

Data Index: 389305 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.8881. Min Act: -0.1700

Data Index: 1304586 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.6673. Min Act: -0.1700

Data Index: 1183128 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.6083. Min Act: -0.1700

Data Index: 891611 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.6340. Min Act: -0.1700

Data Index: 60287 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5958. Min Act: -0.1700

Data Index: 874119 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5626. Min Act: -0.1700

Data Index: 976465 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.6079. Min Act: -0.1700

Data Index: 1231744 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5782. Min Act: -0.1700

Data Index: 37620 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5532. Min Act: -0.1700

Data Index: 1333062 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5444. Min Act: -0.1700

Data Index: 224494 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5057. Min Act: -0.1700

Data Index: 579323 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.5068. Min Act: -0.1700

Data Index: 165497 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4907. Min Act: -0.1700

Data Index: 1330026 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4409. Min Act: -0.1700

Data Index: 792670 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4889. Min Act: -0.1700

Data Index: 910349 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4414. Min Act: -0.1700

Data Index: 735960 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4355. Min Act: -0.1700

Data Index: 187438 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4183. Min Act: -0.1700

Data Index: 461440 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 4.9036. Min Range: -4.9036

Max Act: 4.4131. Min Act: -0.1700

Data Index: 774018 (C4 (Web Text))

Max Activating Token Index: 995