Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 807 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4500. Min Act: -0.1700

Data Index: 478468 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4500. Min Act: -0.1700

Data Index: 1191774 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4343. Min Act: -0.1700

Data Index: 284332 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4186. Min Act: -0.1700

Data Index: 371217 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1260063 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3872. Min Act: -0.1700

Data Index: 960607 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3872. Min Act: -0.1700

Data Index: 668291 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4029. Min Act: -0.1700

Data Index: 86920 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3872. Min Act: -0.1700

Data Index: 903209 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4186. Min Act: -0.1700

Data Index: 385870 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3872. Min Act: -0.1700

Data Index: 180471 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.4186. Min Act: -0.1700

Data Index: 440496 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3715. Min Act: -0.1700

Data Index: 390087 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3558. Min Act: -0.1700

Data Index: 1122273 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3401. Min Act: -0.1700

Data Index: 880956 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3401. Min Act: -0.1700

Data Index: 408813 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3558. Min Act: -0.1700

Data Index: 828409 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3558. Min Act: -0.1700

Data Index: 232103 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3558. Min Act: -0.1700

Data Index: 1014487 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.4500. Min Range: -3.4500

Max Act: 3.3715. Min Act: -0.1700

Data Index: 1022850 (C4 (Web Text))

Max Activating Token Index: 242