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

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

Neuron 846 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: 3.8935. Min Range: -3.8935

Max Act: 3.8935. Min Act: -0.1700

Data Index: 777451 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.8622. Min Act: -0.1700

Data Index: 877048 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.8309. Min Act: -0.1700

Data Index: 610350 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.7684. Min Act: -0.1700

Data Index: 417110 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.7371. Min Act: -0.1700

Data Index: 1020817 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6745. Min Act: -0.1700

Data Index: 121736 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.7371. Min Act: -0.1700

Data Index: 633025 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.7058. Min Act: -0.1700

Data Index: 807566 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 16470 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6119. Min Act: -0.1700

Data Index: 1204688 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1336177 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 367923 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1022257 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 841739 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 534801 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 829983 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1251939 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6119. Min Act: -0.1700

Data Index: 1129073 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6119. Min Act: -0.1700

Data Index: 21197 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 3.8935. Min Range: -3.8935

Max Act: 3.6119. Min Act: -0.1700

Data Index: 541220 (C4 (Web Text))

Max Activating Token Index: 364