Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 892 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.5068. Min Act: -0.1700

Data Index: 935759 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.5068. Min Act: -0.1700

Data Index: 492160 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4911. Min Act: -0.1700

Data Index: 729797 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4754. Min Act: -0.1700

Data Index: 731215 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4598. Min Act: -0.1700

Data Index: 231109 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4441. Min Act: -0.1700

Data Index: 413660 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4598. Min Act: -0.1700

Data Index: 1284766 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4441. Min Act: -0.1700

Data Index: 28661 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4598. Min Act: -0.1700

Data Index: 1072411 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4598. Min Act: -0.1700

Data Index: 537679 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4284. Min Act: -0.1700

Data Index: 1139541 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4441. Min Act: -0.1700

Data Index: 152878 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1331849 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4284. Min Act: -0.1700

Data Index: 1110044 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4284. Min Act: -0.1700

Data Index: 356440 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4284. Min Act: -0.1700

Data Index: 897997 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4127. Min Act: -0.1700

Data Index: 450326 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1090210 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.3970. Min Act: -0.1700

Data Index: 743548 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 3.5068. Min Range: -3.5068

Max Act: 3.3970. Min Act: -0.1700

Data Index: 886767 (C4 (Web Text))

Max Activating Token Index: 570