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

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

Neuron 1292 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: 3.5334. Min Range: -3.5334

Max Act: 3.5178. Min Act: -0.1700

Data Index: 696873 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.5334. Min Act: -0.1700

Data Index: 413439 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4864. Min Act: -0.1700

Data Index: 206050 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.5178. Min Act: -0.1700

Data Index: 43778 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4551. Min Act: -0.1700

Data Index: 834020 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4551. Min Act: -0.1700

Data Index: 95810 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4708. Min Act: -0.1700

Data Index: 1162101 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4551. Min Act: -0.1700

Data Index: 681139 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4551. Min Act: -0.1700

Data Index: 431126 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 604554 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4551. Min Act: -0.1700

Data Index: 403199 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 182255 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 246154 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 562 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 86259 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4708. Min Act: -0.1700

Data Index: 68598 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4394. Min Act: -0.1700

Data Index: 1168149 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4080. Min Act: -0.1700

Data Index: 314649 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4080. Min Act: -0.1700

Data Index: 347271 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 3.5334. Min Range: -3.5334

Max Act: 3.4237. Min Act: -0.1700

Data Index: 790405 (C4 (Web Text))

Max Activating Token Index: 896