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

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

Neuron 559 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: 5.5550. Min Range: -5.5550

Max Act: 5.5550. Min Act: -0.1700

Data Index: 1173624 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.4612. Min Act: -0.1700

Data Index: 464517 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.4925. Min Act: -0.1700

Data Index: 842302 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.4925. Min Act: -0.1700

Data Index: 183651 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.5237. Min Act: -0.1700

Data Index: 1132821 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3675. Min Act: -0.1700

Data Index: 648489 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3675. Min Act: -0.1700

Data Index: 1274269 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.4612. Min Act: -0.1700

Data Index: 1355038 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3675. Min Act: -0.1700

Data Index: 214060 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3050. Min Act: -0.1700

Data Index: 316844 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.2737. Min Act: -0.1700

Data Index: 618366 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3362. Min Act: -0.1700

Data Index: 616119 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3987. Min Act: -0.1700

Data Index: 1257996 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.1800. Min Act: -0.1700

Data Index: 767823 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3362. Min Act: -0.1700

Data Index: 221806 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3675. Min Act: -0.1700

Data Index: 121220 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3050. Min Act: -0.1700

Data Index: 1117144 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3362. Min Act: -0.1700

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3050. Min Act: -0.1700

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 5.5550. Min Range: -5.5550

Max Act: 5.3987. Min Act: -0.1700

Data Index: 361154 (C4 (Web Text))

Max Activating Token Index: 862