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

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

Neuron 892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.5287. Min Act: -0.1700

Data Index: 313657 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.5599. Min Act: -0.1700

Data Index: 750512 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.4037. Min Act: -0.1700

Data Index: 658691 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.4349. Min Act: -0.1700

Data Index: 467658 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3099. Min Act: -0.1700

Data Index: 186427 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 1011218 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 1159638 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 570346 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3099. Min Act: -0.1700

Data Index: 302926 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2787. Min Act: -0.1700

Data Index: 390682 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 1291825 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2787. Min Act: -0.1700

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2162. Min Act: -0.1700

Data Index: 985323 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3099. Min Act: -0.1700

Data Index: 1158487 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 1204592 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2162. Min Act: -0.1700

Data Index: 1271847 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.3412. Min Act: -0.1700

Data Index: 194382 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2787. Min Act: -0.1700

Data Index: 357740 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2474. Min Act: -0.1700

Data Index: 658537 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 5.5599. Min Range: -5.5599

Max Act: 5.2787. Min Act: -0.1700

Data Index: 935350 (C4 (Web Text))

Max Activating Token Index: 787