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

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

Neuron 1082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0225. Min Range: -5.0225

Max Act: 5.0225. Min Act: -0.1700

Data Index: 292030 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.7412. Min Act: -0.1700

Data Index: 1200104 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.6162. Min Act: -0.1700

Data Index: 1107774 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.6474. Min Act: -0.1700

Data Index: 498603 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5693. Min Act: -0.1700

Data Index: 311206 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.6318. Min Act: -0.1700

Data Index: 280747 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5849. Min Act: -0.1700

Data Index: 933181 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5693. Min Act: -0.1700

Data Index: 238667 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.6631. Min Act: -0.1700

Data Index: 1088082 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5849. Min Act: -0.1700

Data Index: 617978 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5381. Min Act: -0.1700

Data Index: 5367 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5693. Min Act: -0.1700

Data Index: 74045 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5537. Min Act: -0.1700

Data Index: 352197 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5381. Min Act: -0.1700

Data Index: 385159 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5381. Min Act: -0.1700

Data Index: 757071 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5537. Min Act: -0.1700

Data Index: 187544 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.4912. Min Act: -0.1700

Data Index: 917976 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5537. Min Act: -0.1700

Data Index: 215393 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5537. Min Act: -0.1700

Data Index: 564803 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5224. Min Act: -0.1700

Data Index: 896264 (C4 (Web Text))

Max Activating Token Index: 445