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

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

Neuron 149 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: 5.4305. Min Range: -5.4305

Max Act: 5.4305. Min Act: -0.1700

Data Index: 841523 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3992. Min Act: -0.1700

Data Index: 66920 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3055. Min Act: -0.1700

Data Index: 1198895 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3992. Min Act: -0.1693

Data Index: 452568 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3367. Min Act: -0.1700

Data Index: 472544 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3680. Min Act: -0.1700

Data Index: 1192808 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3680. Min Act: -0.1700

Data Index: 859084 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3367. Min Act: -0.1700

Data Index: 9199 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3055. Min Act: -0.1700

Data Index: 725651 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3367. Min Act: -0.1700

Data Index: 185985 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.3055. Min Act: -0.1700

Data Index: 980624 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2742. Min Act: -0.1700

Data Index: 1243047 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2430. Min Act: -0.1700

Data Index: 741450 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2742. Min Act: -0.1700

Data Index: 569864 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2742. Min Act: -0.1700

Data Index: 619314 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2117. Min Act: -0.1700

Data Index: 972531 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2430. Min Act: -0.1700

Data Index: 150465 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2430. Min Act: -0.1700

Data Index: 855757 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2430. Min Act: -0.1700

Data Index: 560003 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 5.4305. Min Range: -5.4305

Max Act: 5.2117. Min Act: -0.1700

Data Index: 1211011 (C4 (Web Text))

Max Activating Token Index: 562