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

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

Neuron 597 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: 3.6081. Min Range: -3.6081

Max Act: 3.6081. Min Act: -0.1700

Data Index: 483464 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.5298. Min Act: -0.1700

Data Index: 214381 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.5298. Min Act: -0.1700

Data Index: 4818 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.5298. Min Act: -0.1700

Data Index: 1045732 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.5298. Min Act: -0.1700

Data Index: 760663 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4985. Min Act: -0.1700

Data Index: 944180 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4828. Min Act: -0.1700

Data Index: 268542 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4515. Min Act: -0.1700

Data Index: 844470 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4515. Min Act: -0.1700

Data Index: 685234 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4358. Min Act: -0.1700

Data Index: 766100 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4358. Min Act: -0.1700

Data Index: 192088 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4201. Min Act: -0.1700

Data Index: 213293 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4044. Min Act: -0.1700

Data Index: 10910 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3574. Min Act: -0.1700

Data Index: 650519 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3731. Min Act: -0.1700

Data Index: 617633 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3574. Min Act: -0.1700

Data Index: 665956 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3887. Min Act: -0.1700

Data Index: 333756 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3574. Min Act: -0.1700

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3574. Min Act: -0.1700

Data Index: 944144 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3260. Min Act: -0.1700

Data Index: 162576 (C4 (Web Text))

Max Activating Token Index: 710