Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1795 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.3298. Min Act: -0.1700

Data Index: 623536 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2850. Min Act: -0.1700

Data Index: 104116 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2755. Min Act: -0.1700

Data Index: 562551 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2416. Min Act: -0.1700

Data Index: 709236 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2056. Min Act: -0.1700

Data Index: 1011301 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2225. Min Act: -0.1700

Data Index: 736908 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2251. Min Act: -0.1700

Data Index: 721658 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2110. Min Act: -0.1700

Data Index: 123049 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2030. Min Act: -0.1700

Data Index: 337945 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2046. Min Act: -0.1700

Data Index: 571073 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2261. Min Act: -0.1700

Data Index: 617954 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2004. Min Act: -0.1700

Data Index: 954483 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1285401 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.2058. Min Act: -0.1700

Data Index: 135503 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1903. Min Act: -0.1700

Data Index: 854521 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1750. Min Act: -0.1700

Data Index: 102933 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1925. Min Act: -0.1700

Data Index: 912591 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1690. Min Act: -0.1700

Data Index: 937829 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1610. Min Act: -0.1700

Data Index: 679485 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 3.3298. Min Range: -3.3298

Max Act: 3.1822. Min Act: -0.1700

Data Index: 314663 (C4 (Web Text))

Max Activating Token Index: 300