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

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

Neuron 0 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: 3.2914. Min Range: -3.2914

Max Act: 3.2914. Min Act: -0.1700

Data Index: 176435 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.2442. Min Act: -0.1700

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.2285. Min Act: -0.1700

Data Index: 603726 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1251359 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1183. Min Act: -0.1700

Data Index: 892594 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1341. Min Act: -0.1700

Data Index: 1134948 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1083945 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0868. Min Act: -0.1700

Data Index: 337707 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1026. Min Act: -0.1700

Data Index: 681978 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1026. Min Act: -0.1700

Data Index: 270864 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0710. Min Act: -0.1700

Data Index: 955646 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.1026. Min Act: -0.1700

Data Index: 765013 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0552. Min Act: -0.1700

Data Index: 1262759 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1174637 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0868. Min Act: -0.1700

Data Index: 1098204 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0552. Min Act: -0.1700

Data Index: 1059655 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1137339 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0394. Min Act: -0.1700

Data Index: 422091 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0710. Min Act: -0.1700

Data Index: 652929 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.2914. Min Range: -3.2914

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1281572 (C4 (Web Text))

Max Activating Token Index: 40