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

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

Neuron 458 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: 3.5641. Min Range: -3.5641

Max Act: 3.5641. Min Act: -0.1700

Data Index: 1299406 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4544. Min Act: -0.1700

Data Index: 66676 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4074. Min Act: -0.1700

Data Index: 712401 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3289. Min Act: -0.1700

Data Index: 1152210 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3289. Min Act: -0.1700

Data Index: 685517 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1195801 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1202259 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2504. Min Act: -0.1700

Data Index: 854336 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1325735 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2347. Min Act: -0.1700

Data Index: 757226 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2189. Min Act: -0.1700

Data Index: 1087183 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2032. Min Act: -0.1700

Data Index: 1298480 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2347. Min Act: -0.1700

Data Index: 994964 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2032. Min Act: -0.1700

Data Index: 10509 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1717. Min Act: -0.1700

Data Index: 37766 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2032. Min Act: -0.1700

Data Index: 1277593 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2032. Min Act: -0.1700

Data Index: 394115 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2189. Min Act: -0.1700

Data Index: 519919 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1402. Min Act: -0.1700

Data Index: 48208 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1226331 (C4 (Web Text))

Max Activating Token Index: 182