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

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

Neuron 1791 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: 3.3231. Min Range: -3.3231

Max Act: 3.3231. Min Act: -0.1700

Data Index: 930789 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.2643. Min Act: -0.1700

Data Index: 1648531 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1728. Min Act: -0.1700

Data Index: 434676 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1172. Min Act: -0.1700

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1035. Min Act: -0.1700

Data Index: 922196 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1235. Min Act: -0.1700

Data Index: 347012 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1114. Min Act: -0.1700

Data Index: 1389824 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1146. Min Act: -0.1700

Data Index: 957515 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1027762 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1172597 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0900. Min Act: -0.1700

Data Index: 1194094 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.1124. Min Act: -0.1700

Data Index: 422436 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0945. Min Act: -0.1700

Data Index: 601740 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0848. Min Act: -0.1700

Data Index: 424655 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0928. Min Act: -0.1700

Data Index: 1079139 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0945. Min Act: -0.1700

Data Index: 548 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0633. Min Act: -0.1700

Data Index: 310803 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0928. Min Act: -0.1700

Data Index: 365357 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0700. Min Act: -0.1700

Data Index: 32057 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 3.3231. Min Range: -3.3231

Max Act: 3.0714. Min Act: -0.1700

Data Index: 558284 (C4 (Web Text))

Max Activating Token Index: 455