Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1088 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.1057. Min Act: -0.1700

Data Index: 542192 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0900. Min Act: -0.1700

Data Index: 876579 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0742. Min Act: -0.1700

Data Index: 407283 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0900. Min Act: -0.1700

Data Index: 978265 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0426. Min Act: -0.1700

Data Index: 1169932 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0426. Min Act: -0.1700

Data Index: 699117 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0110. Min Act: -0.1700

Data Index: 654614 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0742. Min Act: -0.1700

Data Index: 1338147 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0110. Min Act: -0.1700

Data Index: 146094 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9794. Min Act: -0.1700

Data Index: 366266 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1175173 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9952. Min Act: -0.1700

Data Index: 605698 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9636. Min Act: -0.1700

Data Index: 1352186 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1163242 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9794. Min Act: -0.1700

Data Index: 418016 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9952. Min Act: -0.1700

Data Index: 432492 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9636. Min Act: -0.1700

Data Index: 980283 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9794. Min Act: -0.1700

Data Index: 988966 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9478. Min Act: -0.1700

Data Index: 1160143 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9636. Min Act: -0.1700

Data Index: 108769 (C4 (Web Text))

Max Activating Token Index: 967