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

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

Neuron 935 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: 5.6052. Min Range: -5.6052

Max Act: 5.6052. Min Act: -0.1700

Data Index: 592763 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.5740. Min Act: -0.1618

Data Index: 1264768 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.5427. Min Act: -0.1699

Data Index: 929135 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4802. Min Act: -0.1700

Data Index: 749396 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.5115. Min Act: -0.1700

Data Index: 374465 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.5115. Min Act: -0.1700

Data Index: 641575 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4490. Min Act: -0.1697

Data Index: 999940 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4177. Min Act: -0.1700

Data Index: 873931 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4177. Min Act: -0.1700

Data Index: 1267247 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4177. Min Act: -0.1700

Data Index: 1009814 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1219671 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 344171 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2615. Min Act: -0.1699

Data Index: 1353553 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2927. Min Act: -0.1699

Data Index: 1056307 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2302. Min Act: -0.1700

Data Index: 1052840 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2615. Min Act: -0.1700

Data Index: 98241 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2927. Min Act: -0.1700

Data Index: 162243 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2615. Min Act: -0.1699

Data Index: 1341410 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.1677. Min Act: -0.1700

Data Index: 1352810 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2302. Min Act: -0.1700

Data Index: 1173658 (C4 (Web Text))

Max Activating Token Index: 21