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

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

Neuron 1682 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: 3.8385. Min Range: -3.8385

Max Act: 3.8385. Min Act: -0.1700

Data Index: 63299 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6821. Min Act: -0.1700

Data Index: 366086 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.7134. Min Act: -0.1700

Data Index: 614706 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.7134. Min Act: -0.1700

Data Index: 1175704 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6821. Min Act: -0.1700

Data Index: 805334 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6821. Min Act: -0.1700

Data Index: 1026087 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6508. Min Act: -0.1700

Data Index: 1146575 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6508. Min Act: -0.1700

Data Index: 1277778 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 656202 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 795488 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6195. Min Act: -0.1700

Data Index: 55158 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 168722 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.6195. Min Act: -0.1700

Data Index: 1327792 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 744147 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 782661 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5882. Min Act: -0.1700

Data Index: 318055 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5569. Min Act: -0.1700

Data Index: 670846 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5255. Min Act: -0.1700

Data Index: 639785 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5569. Min Act: -0.1700

Data Index: 169761 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 3.8385. Min Range: -3.8385

Max Act: 3.5569. Min Act: -0.1700

Data Index: 797335 (C4 (Web Text))

Max Activating Token Index: 690