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

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

Neuron 561 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: 5.2532. Min Range: -5.2532

Max Act: 5.2532. Min Act: -0.1700

Data Index: 946523 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2532. Min Act: -0.1700

Data Index: 432443 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2532. Min Act: -0.1700

Data Index: 890331 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 335646 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 787031 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 1037736 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 214384 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 386649 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.2220. Min Act: -0.1700

Data Index: 1012721 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1907. Min Act: -0.1700

Data Index: 533121 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1595. Min Act: -0.1700

Data Index: 1357925 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1907. Min Act: -0.1700

Data Index: 1211964 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1595. Min Act: -0.1700

Data Index: 233797 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1595. Min Act: -0.1700

Data Index: 227584 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1595. Min Act: -0.1700

Data Index: 806180 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1595. Min Act: -0.1700

Data Index: 1046130 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1282. Min Act: -0.1700

Data Index: 1250469 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1282. Min Act: -0.1700

Data Index: 298240 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1282. Min Act: -0.1700

Data Index: 1141316 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 5.2532. Min Range: -5.2532

Max Act: 5.1282. Min Act: -0.1700

Data Index: 994836 (C4 (Web Text))

Max Activating Token Index: 780