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

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

Neuron 291 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: 7.1692. Min Range: -7.1692

Max Act: 7.1692. Min Act: -0.1700

Data Index: 139038 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.8255. Min Act: -0.1700

Data Index: 765698 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.9192. Min Act: -0.1700

Data Index: 1152448 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.7005. Min Act: -0.1700

Data Index: 690293 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.6692. Min Act: -0.1700

Data Index: 1359151 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5755. Min Act: -0.1700

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5442. Min Act: -0.1699

Data Index: 208097 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.6067. Min Act: -0.1700

Data Index: 568873 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.6067. Min Act: -0.1700

Data Index: 1356581 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5130. Min Act: -0.1700

Data Index: 257425 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5442. Min Act: -0.1700

Data Index: 412713 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5442. Min Act: -0.1700

Data Index: 1298250 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.5130. Min Act: -0.1700

Data Index: 100024 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1700

Data Index: 1144082 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4192. Min Act: -0.1700

Data Index: 183165 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1700

Data Index: 54516 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1700

Data Index: 1044530 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1700

Data Index: 792688 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1699

Data Index: 1171175 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 7.1692. Min Range: -7.1692

Max Act: 6.4817. Min Act: -0.1700

Data Index: 1105436 (C4 (Web Text))

Max Activating Token Index: 324