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

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

Neuron 1179 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: 3.1258. Min Range: -3.1258

Max Act: 3.1258. Min Act: -0.1700

Data Index: 533529 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.1258. Min Act: -0.1700

Data Index: 456682 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.1101. Min Act: -0.1700

Data Index: 1092645 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0785. Min Act: -0.1700

Data Index: 58033 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0943. Min Act: -0.1700

Data Index: 718208 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0470. Min Act: -0.1700

Data Index: 485980 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0154. Min Act: -0.1700

Data Index: 1099860 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9996. Min Act: -0.1700

Data Index: 177136 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9996. Min Act: -0.1700

Data Index: 1164545 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9996. Min Act: -0.1700

Data Index: 272741 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0154. Min Act: -0.1700

Data Index: 35689 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9996. Min Act: -0.1700

Data Index: 662652 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.1258. Min Range: -3.1258

Max Act: 3.0154. Min Act: -0.1700

Data Index: 5122 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9838. Min Act: -0.1700

Data Index: 233621 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9838. Min Act: -0.1700

Data Index: 1240057 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9838. Min Act: -0.1700

Data Index: 785914 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9838. Min Act: -0.1700

Data Index: 1013987 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9679. Min Act: -0.1700

Data Index: 759635 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9679. Min Act: -0.1700

Data Index: 915617 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 3.1258. Min Range: -3.1258

Max Act: 2.9679. Min Act: -0.1700

Data Index: 17298 (C4 (Web Text))

Max Activating Token Index: 340