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

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

Neuron 1003 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: 5.2542. Min Range: -5.2542

Max Act: 5.2542. Min Act: -0.1700

Data Index: 84254 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.2542. Min Act: -0.1700

Data Index: 367739 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.2230. Min Act: -0.1700

Data Index: 653233 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.1917. Min Act: -0.1700

Data Index: 104123 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.2230. Min Act: -0.1700

Data Index: 60563 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.1292. Min Act: -0.1700

Data Index: 755752 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9730. Min Act: -0.1700

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0042. Min Act: -0.1700

Data Index: 514388 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9730. Min Act: -0.1700

Data Index: 292278 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9730. Min Act: -0.1700

Data Index: 207671 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9417. Min Act: -0.1700

Data Index: 1155531 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8480. Min Act: -0.1700

Data Index: 1350660 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9105. Min Act: -0.1700

Data Index: 496546 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8480. Min Act: -0.1700

Data Index: 1356528 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8480. Min Act: -0.1700

Data Index: 398855 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8167. Min Act: -0.1700

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8480. Min Act: -0.1700

Data Index: 408816 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.7542. Min Act: -0.1700

Data Index: 1239183 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.8167. Min Act: -0.1700

Data Index: 340504 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.7542. Min Act: -0.1700

Data Index: 786457 (C4 (Web Text))

Max Activating Token Index: 953