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

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

Neuron 782 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6275. Min Act: -0.1700

Data Index: 792110 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6100. Min Act: -0.1700

Data Index: 317654 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6100. Min Act: -0.1700

Data Index: 966442 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6013. Min Act: -0.1700

Data Index: 541855 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6013. Min Act: -0.1700

Data Index: 931202 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5751. Min Act: -0.1700

Data Index: 985536 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5839. Min Act: -0.1700

Data Index: 508971 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5576. Min Act: -0.1700

Data Index: 582345 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5489. Min Act: -0.1700

Data Index: 205040 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5401. Min Act: -0.1700

Data Index: 578815 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5489. Min Act: -0.1700

Data Index: 971071 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5401. Min Act: -0.1700

Data Index: 627018 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5314. Min Act: -0.1700

Data Index: 107664 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5314. Min Act: -0.1700

Data Index: 397826 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5314. Min Act: -0.1700

Data Index: 899261 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5226. Min Act: -0.1700

Data Index: 1249512 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5226. Min Act: -0.1700

Data Index: 831824 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5226. Min Act: -0.1700

Data Index: 680700 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5314. Min Act: -0.1700

Data Index: 627296 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.5138. Min Act: -0.1700

Data Index: 776217 (C4 (Web Text))

Max Activating Token Index: 25