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

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

Neuron 1366 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0600. Min Range: -6.0600

Max Act: 6.0600. Min Act: -0.1700

Data Index: 616127 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.8100. Min Act: -0.1700

Data Index: 453037 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.7475. Min Act: -0.1700

Data Index: 973079 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.7788. Min Act: -0.1700

Data Index: 998967 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.7163. Min Act: -0.1700

Data Index: 830340 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.7163. Min Act: -0.1700

Data Index: 1266436 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6538. Min Act: -0.1700

Data Index: 430555 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6850. Min Act: -0.1700

Data Index: 1105134 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6850. Min Act: -0.1700

Data Index: 141256 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6538. Min Act: -0.1700

Data Index: 929883 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6225. Min Act: -0.1700

Data Index: 105721 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6538. Min Act: -0.1700

Data Index: 1262414 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6225. Min Act: -0.1700

Data Index: 32501 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.5913. Min Act: -0.1700

Data Index: 549209 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6538. Min Act: -0.1700

Data Index: 660495 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.5600. Min Act: -0.1700

Data Index: 1156917 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6225. Min Act: -0.1700

Data Index: 397639 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.5913. Min Act: -0.1700

Data Index: 644487 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.6225. Min Act: -0.1700

Data Index: 324613 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 6.0600. Min Range: -6.0600

Max Act: 5.5913. Min Act: -0.1700

Data Index: 322751 (C4 (Web Text))

Max Activating Token Index: 50