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

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

Neuron 1183 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: 5.6184. Min Range: -5.6184

Max Act: 5.6184. Min Act: -0.1697

Data Index: 1025959 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.5247. Min Act: -0.1668

Data Index: 785159 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3997. Min Act: -0.1699

Data Index: 1162598 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3684. Min Act: -0.1700

Data Index: 219123 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3372. Min Act: -0.1699

Data Index: 1317358 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3372. Min Act: -0.1460

Data Index: 376576 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3372. Min Act: -0.1700

Data Index: 484907 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3059. Min Act: -0.1700

Data Index: 895217 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3059. Min Act: -0.1699

Data Index: 520659 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3059. Min Act: -0.1693

Data Index: 813609 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2747. Min Act: -0.1700

Data Index: 979484 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2434. Min Act: -0.1700

Data Index: 980954 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2122. Min Act: -0.1700

Data Index: 509383 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2434. Min Act: -0.1699

Data Index: 45381 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2434. Min Act: -0.1700

Data Index: 993645 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2434. Min Act: -0.1577

Data Index: 1162059 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2122. Min Act: -0.1698

Data Index: 1205287 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.1497. Min Act: -0.1671

Data Index: 819771 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.1809. Min Act: -0.1700

Data Index: 979529 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.2122. Min Act: -0.1699

Data Index: 22427 (C4 (Web Text))

Max Activating Token Index: 758