Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1299 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.8737. Min Act: -0.1700

Data Index: 1133233 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.7800. Min Act: -0.1700

Data Index: 767626 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.8737. Min Act: -0.1700

Data Index: 652061 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.7487. Min Act: -0.1700

Data Index: 299508 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.6237. Min Act: -0.1700

Data Index: 683538 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.6862. Min Act: -0.1700

Data Index: 501023 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.5925. Min Act: -0.1700

Data Index: 567572 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.5612. Min Act: -0.1700

Data Index: 1295565 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4675. Min Act: -0.1700

Data Index: 318761 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.5300. Min Act: -0.1700

Data Index: 80502 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.5300. Min Act: -0.1700

Data Index: 453016 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4675. Min Act: -0.1700

Data Index: 718844 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4675. Min Act: -0.1700

Data Index: 35782 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4050. Min Act: -0.1700

Data Index: 188988 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.3737. Min Act: -0.1700

Data Index: 604905 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1064949 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4050. Min Act: -0.1700

Data Index: 147189 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4362. Min Act: -0.1700

Data Index: 231797 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4050. Min Act: -0.1700

Data Index: 677492 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 5.8737. Min Range: -5.8737

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1197930 (C4 (Web Text))

Max Activating Token Index: 542