Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.9820. Min Act: -0.1700

Data Index: 1239183 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.8882. Min Act: -0.1700

Data Index: 298048 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7631. Min Act: -0.1700

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 466781 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7944. Min Act: -0.1700

Data Index: 921314 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.8256. Min Act: -0.1700

Data Index: 1072333 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.8100. Min Act: -0.1700

Data Index: 1309731 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.8100. Min Act: -0.1700

Data Index: 978153 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7631. Min Act: -0.1700

Data Index: 329587 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7787. Min Act: -0.1700

Data Index: 224325 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7161. Min Act: -0.1700

Data Index: 504271 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.6692. Min Act: -0.1700

Data Index: 618264 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 416516 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 553316 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 1128186 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 1069540 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7318. Min Act: -0.1700

Data Index: 507991 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7161. Min Act: -0.1700

Data Index: 595440 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7005. Min Act: -0.1700

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 3.9820. Min Range: -3.9820

Max Act: 3.7474. Min Act: -0.1700

Data Index: 831526 (C4 (Web Text))

Max Activating Token Index: 46