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

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

Neuron 541 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.3579. Min Act: -0.1700

Data Index: 759830 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2637. Min Act: -0.1700

Data Index: 582005 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2165. Min Act: -0.1700

Data Index: 219522 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2008. Min Act: -0.1700

Data Index: 553982 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1850. Min Act: -0.1700

Data Index: 990236 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2008. Min Act: -0.1700

Data Index: 1106067 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1850. Min Act: -0.1700

Data Index: 17876 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1850. Min Act: -0.1700

Data Index: 192805 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1304212 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1535. Min Act: -0.1700

Data Index: 486596 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1039021 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1693. Min Act: -0.1700

Data Index: 1102338 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1495419 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1693. Min Act: -0.1700

Data Index: 289352 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 934699 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 759146 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 67290 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 583260 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1056928 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1220. Min Act: -0.1700

Data Index: 858273 (C4 (Web Text))

Max Activating Token Index: 710