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

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

Neuron 1123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1472. Min Range: -4.1472

Max Act: 4.1472. Min Act: -0.1700

Data Index: 770549 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.9127. Min Act: -0.1700

Data Index: 880717 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.8971. Min Act: -0.1700

Data Index: 806936 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.8814. Min Act: -0.1700

Data Index: 622339 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.8189. Min Act: -0.1700

Data Index: 1322031 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7876. Min Act: -0.1700

Data Index: 1143351 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7094. Min Act: -0.1700

Data Index: 203315 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6311. Min Act: -0.1700

Data Index: 1137033 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7406. Min Act: -0.1700

Data Index: 865352 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7250. Min Act: -0.1700

Data Index: 278287 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6781. Min Act: -0.1700

Data Index: 496075 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7719. Min Act: -0.1700

Data Index: 405603 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6937. Min Act: -0.1700

Data Index: 554925 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6937. Min Act: -0.1700

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6468. Min Act: -0.1700

Data Index: 888460 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6468. Min Act: -0.1700

Data Index: 218821 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.7250. Min Act: -0.1700

Data Index: 1101685 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6624. Min Act: -0.1700

Data Index: 1152094 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6624. Min Act: -0.1700

Data Index: 136199 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 4.1472. Min Range: -4.1472

Max Act: 3.6781. Min Act: -0.1700

Data Index: 652783 (C4 (Web Text))

Max Activating Token Index: 508