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

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

Neuron 2007 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.9240. Min Act: -0.1700

Data Index: 741237 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.7990. Min Act: -0.1700

Data Index: 592923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.6740. Min Act: -0.1700

Data Index: 308914 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.6427. Min Act: -0.1700

Data Index: 230001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5490. Min Act: -0.1700

Data Index: 1053176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5490. Min Act: -0.1700

Data Index: 829585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5177. Min Act: -0.1700

Data Index: 1291242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4865. Min Act: -0.1700

Data Index: 723879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.5490. Min Act: -0.1700

Data Index: 823687 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4240. Min Act: -0.1700

Data Index: 1043604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.4240. Min Act: -0.1700

Data Index: 1153711 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.3615. Min Act: -0.1700

Data Index: 182161 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.3615. Min Act: -0.1700

Data Index: 362738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.3927. Min Act: -0.1700

Data Index: 1043425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.2990. Min Act: -0.1700

Data Index: 1290735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.2990. Min Act: -0.1700

Data Index: 533033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.2677. Min Act: -0.1700

Data Index: 1317315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.3615. Min Act: -0.1700

Data Index: 1012714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.2990. Min Act: -0.1700

Data Index: 139508 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.9240. Min Range: -4.9240

Max Act: 4.2052. Min Act: -0.1700

Data Index: 626433 (C4 (Web Text))

Max Activating Token Index: 1023