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

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

Neuron 72 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.2479. Min Act: -0.1700

Data Index: 430059 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.2321. Min Act: -0.1700

Data Index: 437469 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.2164. Min Act: -0.1700

Data Index: 494796 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.2007. Min Act: -0.1700

Data Index: 540706 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1850. Min Act: -0.1700

Data Index: 364241 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1692. Min Act: -0.1700

Data Index: 485976 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.2164. Min Act: -0.1700

Data Index: 982002 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1535. Min Act: -0.1700

Data Index: 629186 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1535. Min Act: -0.1700

Data Index: 1206370 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1377. Min Act: -0.1700

Data Index: 1185058 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1230557 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1377. Min Act: -0.1700

Data Index: 1152157 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1535. Min Act: -0.1700

Data Index: 1127006 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1140468 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1220. Min Act: -0.1700

Data Index: 371197 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1062. Min Act: -0.1700

Data Index: 849494 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1062. Min Act: -0.1700

Data Index: 991962 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.0904. Min Act: -0.1700

Data Index: 1295038 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1062. Min Act: -0.1700

Data Index: 474246 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 3.2479. Min Range: -3.2479

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1314795 (C4 (Web Text))

Max Activating Token Index: 958