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

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

Neuron 1869 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: 3.6476. Min Range: -3.6476

Max Act: 3.6163. Min Act: -0.1700

Data Index: 87652 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.6476. Min Act: -0.1700

Data Index: 40301 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5850. Min Act: -0.1700

Data Index: 900101 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 255158 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1252195 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 436333 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 1083956 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5850. Min Act: -0.1700

Data Index: 111815 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 961945 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 207142 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5223. Min Act: -0.1700

Data Index: 704208 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5223. Min Act: -0.1700

Data Index: 344909 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 11423 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 439017 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5223. Min Act: -0.1700

Data Index: 1207459 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 74047 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 192128 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4753. Min Act: -0.1700

Data Index: 60071 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 1058319 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 807346 (C4 (Web Text))

Max Activating Token Index: 10