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

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

Neuron 395 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: 3.8204. Min Range: -3.8204

Max Act: 3.8204. Min Act: -0.1700

Data Index: 613976 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.8204. Min Act: -0.1700

Data Index: 120467 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.8204. Min Act: -0.1700

Data Index: 543415 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7891. Min Act: -0.1700

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7891. Min Act: -0.1700

Data Index: 242765 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 44556 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7578. Min Act: -0.1700

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7578. Min Act: -0.1700

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 1163343 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 615294 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7578. Min Act: -0.1700

Data Index: 1080648 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.6952. Min Act: -0.1700

Data Index: 1224908 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 46194 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 715941 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 439672 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.7265. Min Act: -0.1700

Data Index: 1033110 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.6952. Min Act: -0.1700

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.6952. Min Act: -0.1700

Data Index: 269245 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.6639. Min Act: -0.1700

Data Index: 690648 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.8204. Min Range: -3.8204

Max Act: 3.6952. Min Act: -0.1700

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 189