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

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

Neuron 582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.9872. Min Act: -0.1700

Data Index: 870459 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.9247. Min Act: -0.1700

Data Index: 30329 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 209256 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8621. Min Act: -0.1700

Data Index: 947252 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 705356 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 1087556 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 571238 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 849770 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7996. Min Act: -0.1700

Data Index: 1322377 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7214. Min Act: -0.1700

Data Index: 65491 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7996. Min Act: -0.1700

Data Index: 1025224 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7996. Min Act: -0.1700

Data Index: 555521 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7683. Min Act: -0.1700

Data Index: 980302 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.8309. Min Act: -0.1700

Data Index: 362133 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7057. Min Act: -0.1700

Data Index: 987969 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7683. Min Act: -0.1700

Data Index: 516869 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7683. Min Act: -0.1700

Data Index: 769622 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7527. Min Act: -0.1700

Data Index: 1096530 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7370. Min Act: -0.1700

Data Index: 459019 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.9872. Min Range: -3.9872

Max Act: 3.7370. Min Act: -0.1700

Data Index: 217560 (C4 (Web Text))

Max Activating Token Index: 600