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

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

Neuron 670 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: 4.0819. Min Range: -4.0819

Max Act: 4.0819. Min Act: -0.1700

Data Index: 1007983 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 4.0819. Min Range: -4.0819

Max Act: 4.0445. Min Act: -0.1700

Data Index: 389960 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9955. Min Act: -0.1700

Data Index: 941430 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9786. Min Act: -0.1700

Data Index: 467610 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9666. Min Act: -0.1700

Data Index: 1061116 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9328. Min Act: -0.1700

Data Index: 880118 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9678. Min Act: -0.1700

Data Index: 1094671 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9293. Min Act: -0.1700

Data Index: 394582 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9253. Min Act: -0.1700

Data Index: 710126 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9039. Min Act: -0.1699

Data Index: 1010182 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9021. Min Act: -0.1700

Data Index: 840139 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9185. Min Act: -0.1700

Data Index: 399055 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.9124. Min Act: -0.1700

Data Index: 227384 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8898. Min Act: -0.1700

Data Index: 1185431 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8781. Min Act: -0.1700

Data Index: 1215954 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8980. Min Act: -0.1700

Data Index: 1287902 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8921. Min Act: -0.1700

Data Index: 1268997 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8938. Min Act: -0.1700

Data Index: 246600 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8501. Min Act: -0.1700

Data Index: 1136962 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 4.0819. Min Range: -4.0819

Max Act: 3.8528. Min Act: -0.1700

Data Index: 596435 (C4 (Web Text))

Max Activating Token Index: 789