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

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

Neuron 1553 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: 3.5616. Min Range: -3.5616

Max Act: 3.5616. Min Act: -0.1700

Data Index: 758138 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.5459. Min Act: -0.1700

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.5146. Min Act: -0.1700

Data Index: 912497 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.5146. Min Act: -0.1700

Data Index: 529620 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4989. Min Act: -0.1700

Data Index: 981654 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4833. Min Act: -0.1699

Data Index: 1228081 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4676. Min Act: -0.1700

Data Index: 1040066 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4833. Min Act: -0.1700

Data Index: 1303187 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4833. Min Act: -0.1700

Data Index: 255028 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4989. Min Act: -0.1700

Data Index: 1201231 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4833. Min Act: -0.1700

Data Index: 1078277 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4676. Min Act: -0.1700

Data Index: 679592 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4519. Min Act: -0.1700

Data Index: 57282 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4519. Min Act: -0.1700

Data Index: 1228794 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4519. Min Act: -0.1700

Data Index: 277937 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4363. Min Act: -0.1700

Data Index: 1347331 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4519. Min Act: -0.1700

Data Index: 799440 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4206. Min Act: -0.1700

Data Index: 963366 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4206. Min Act: -0.1700

Data Index: 322613 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.4206. Min Act: -0.1700

Data Index: 9501 (C4 (Web Text))

Max Activating Token Index: 748