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

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

Neuron 348 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.7592. Min Act: -0.1700

Data Index: 503740 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.7279. Min Act: -0.1700

Data Index: 542262 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6966. Min Act: -0.1700

Data Index: 634399 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 770564 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6653. Min Act: -0.1700

Data Index: 89841 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6653. Min Act: -0.1700

Data Index: 1246639 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 515533 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6653. Min Act: -0.1700

Data Index: 452182 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 152608 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6653. Min Act: -0.1700

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 236615 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 203870 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 832776 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 245589 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 457578 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6027. Min Act: -0.1700

Data Index: 1353065 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6653. Min Act: -0.1700

Data Index: 122762 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6340. Min Act: -0.1700

Data Index: 497580 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6027. Min Act: -0.1700

Data Index: 62119 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6027. Min Act: -0.1700

Data Index: 178737 (C4 (Web Text))

Max Activating Token Index: 765