Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1735 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0945. Min Range: -3.0945

Max Act: 3.0945. Min Act: -0.1700

Data Index: 522221 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.0945. Min Range: -3.0945

Max Act: 3.0471. Min Act: -0.1700

Data Index: 927030 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.9997. Min Act: -0.1700

Data Index: 733952 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.9839. Min Act: -0.1700

Data Index: 300877 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.8412. Min Act: -0.1700

Data Index: 557416 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.8412. Min Act: -0.1700

Data Index: 862274 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.8253. Min Act: -0.1700

Data Index: 154159 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.8094. Min Act: -0.1700

Data Index: 929611 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.8094. Min Act: -0.1700

Data Index: 757052 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7775. Min Act: -0.1700

Data Index: 422703 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7775. Min Act: -0.1700

Data Index: 1101294 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7297. Min Act: -0.1700

Data Index: 561543 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7775. Min Act: -0.1700

Data Index: 267973 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7616. Min Act: -0.1700

Data Index: 1086667 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7456. Min Act: -0.1700

Data Index: 624060 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7297. Min Act: -0.1700

Data Index: 711269 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7297. Min Act: -0.1700

Data Index: 951439 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7137. Min Act: -0.1700

Data Index: 1233123 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.6977. Min Act: -0.1700

Data Index: 1288879 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.0945. Min Range: -3.0945

Max Act: 2.7137. Min Act: -0.1700

Data Index: 512770 (C4 (Web Text))

Max Activating Token Index: 23