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

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

Neuron 11 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0828. Min Act: -0.1700

Data Index: 294861 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0828. Min Act: -0.1700

Data Index: 484983 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0670. Min Act: -0.1700

Data Index: 383792 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0670. Min Act: -0.1700

Data Index: 264518 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0670. Min Act: -0.1700

Data Index: 862583 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0512. Min Act: -0.1700

Data Index: 959302 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0512. Min Act: -0.1700

Data Index: 395685 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 905728 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 919572 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 514449 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1160755 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 258989 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0038. Min Act: -0.1700

Data Index: 10189 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 1207072 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0038. Min Act: -0.1700

Data Index: 4123 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.0828. Min Range: -3.0828

Max Act: 2.9880. Min Act: -0.1700

Data Index: 1216896 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.0828. Min Range: -3.0828

Max Act: 3.0197. Min Act: -0.1700

Data Index: 472260 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.0828. Min Range: -3.0828

Max Act: 2.9722. Min Act: -0.1700

Data Index: 744941 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 3.0828. Min Range: -3.0828

Max Act: 2.9722. Min Act: -0.1700

Data Index: 114605 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.0828. Min Range: -3.0828

Max Act: 2.9880. Min Act: -0.1700

Data Index: 337561 (C4 (Web Text))

Max Activating Token Index: 505