Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1250 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.6001. Min Act: -0.1700

Data Index: 1001975 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.5219. Min Act: -0.1700

Data Index: 641599 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.3657. Min Act: -0.1700

Data Index: 1009778 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1938. Min Act: -0.1700

Data Index: 794446 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1782. Min Act: -0.1700

Data Index: 258357 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1313. Min Act: -0.1700

Data Index: 1335538 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1001. Min Act: -0.1700

Data Index: 1210706 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1313. Min Act: -0.1700

Data Index: 188217 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.1313. Min Act: -0.1700

Data Index: 922097 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 5.6001. Min Range: -5.6001

Max Act: 5.0844. Min Act: -0.1700

Data Index: 613907 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9438. Min Act: -0.1700

Data Index: 968383 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9594. Min Act: -0.1700

Data Index: 228035 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.7251. Min Act: -0.1700

Data Index: 1355264 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9594. Min Act: -0.1700

Data Index: 1166715 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9126. Min Act: -0.1700

Data Index: 732146 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.8813. Min Act: -0.1700

Data Index: 430821 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9438. Min Act: -0.1700

Data Index: 1213122 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.8344. Min Act: -0.1700

Data Index: 1204240 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.8657. Min Act: -0.1700

Data Index: 876746 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 5.6001. Min Range: -5.6001

Max Act: 4.9438. Min Act: -0.1700

Data Index: 91897 (C4 (Web Text))

Max Activating Token Index: 204