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

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

Neuron 870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1343. Min Range: -5.1343

Max Act: 5.1343. Min Act: -0.1700

Data Index: 157253 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.8843. Min Act: -0.1700

Data Index: 127503 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.9000. Min Act: -0.1700

Data Index: 700902 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.7593. Min Act: -0.1700

Data Index: 384386 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.7125. Min Act: -0.1700

Data Index: 1121518 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.6343. Min Act: -0.1700

Data Index: 1056292 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.6187. Min Act: -0.1700

Data Index: 3350 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.5875. Min Act: -0.1700

Data Index: 386923 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.5093. Min Act: -0.1700

Data Index: 553736 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.5093. Min Act: -0.1700

Data Index: 58577 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4781. Min Act: -0.1700

Data Index: 145596 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4156. Min Act: -0.1700

Data Index: 1236882 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4781. Min Act: -0.1700

Data Index: 825732 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4781. Min Act: -0.1700

Data Index: 357654 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4468. Min Act: -0.1700

Data Index: 265453 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4156. Min Act: -0.1700

Data Index: 1313533 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4468. Min Act: -0.1700

Data Index: 801123 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4624. Min Act: -0.1700

Data Index: 877940 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4624. Min Act: -0.1700

Data Index: 860516 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 5.1343. Min Range: -5.1343

Max Act: 4.4312. Min Act: -0.1700

Data Index: 383510 (C4 (Web Text))

Max Activating Token Index: 623